© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65781
    Prev
    Next
    INDEX
    Explanations

    must reproduce

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

    software license requirements about redistributing code in binary form.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    íteni
    -0.88
     "/",
    -0.85
    ratos
    -0.85
    osomal
    -0.84
    thargy
    -0.83
    RTHOOK
    -0.83
    曉
    -0.83
     CascadeType
    -0.82
    atorial
    -0.81
     ''){
    -0.81
    POSITIVE LOGITS
     the
    0.82
     sfr
    0.82
     blah
    0.77
     Bildschirm
    0.74
     ausge
    0.72
     embedded
    0.72
     Unterschied
    0.72
     packed
    0.72
     latest
    0.71
    сё
    0.70
    Activations Density 0.001%

    No Known Activations