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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66353
    Prev
    Next
    INDEX
    Explanations

    file components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     aviones
    -1.43
     Naciones
    -1.41
     cantantes
    -1.40
     pelu
    -1.38
    ऎ
    -1.38
     calça
    -1.36
     bordado
    -1.35
     banho
    -1.33
     évé
    -1.33
    cauc
    -1.31
    POSITIVE LOGITS
    r
    1.74
    u
    1.69
    er
    1.65
    _
    1.63
    on
    1.61
    o
    1.60
    is
    1.59
    p
    1.59
    D
    1.55
    O
    1.55
    Activations Density 0.004%

    No Known Activations