© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111330
    Prev
    Next
    INDEX
    Explanations

    `List`, `profile`

    np_acts-logits-general · gemini-2.5-flash-lite

    special formatting characters or markers that indicate structural elements in code or documentation, particularly backslashes and arrows used in technical documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     essenciais
    -1.98
     originais
    -1.93
    для
    -1.84
    ?”
    -1.74
     especiais
    -1.70
     Наталья
    -1.67
     adicionais
    -1.64
     таких
    -1.63
     necessários
    -1.62
     atuais
    -1.60
    POSITIVE LOGITS
     it
    2.19
     in
    2.08
     on
    1.84
     this
    1.80
     know
    1.73
     by
    1.72
     same
    1.70
     from
    1.66
    ch
    1.65
     the
    1.63
    Activations Density 0.001%

    No Known Activations