© 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. 34-GEMMASCOPE-RES-131K
    7. 92604
    Prev
    Next
    INDEX
    Explanations

    standard input/output

    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_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
     stdin
    -1.05
     subsequence
    -0.86
    exit
    -0.85
    Normalize
    -0.83
    deep
    -0.82
    pushFollow
    -0.81
     Scanner
    -0.80
    内部
    -0.80
    입
    -0.80
    ceae
    -0.79
    POSITIVE LOGITS
    Доброго
    0.83
    IGO
    0.82
    Mikey
    0.82
    AndFlush
    0.82
    宝石
    0.81
    Buen
    0.80
    強烈
    0.80
    Rook
    0.79
    🤣🤣
    0.77
     jugend
    0.77
    Activations Density 0.016%

    No Known Activations