© 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. 89947
    Prev
    Next
    INDEX
    Explanations

    identification and claims

    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
     who
    -0.96
    burgs
    -0.94
     their
    -0.94
    olarmente
    -0.92
     TÉCNICA
    -0.89
    ノブ
    -0.85
    ichtete
    -0.84
    żar
    -0.84
     seemingly
    -0.82
     animada
    -0.82
    POSITIVE LOGITS
    gänger
    0.97
    dengan
    0.87
    becomes
    0.85
    ellation
    0.85
    zzi
    0.84
    inspiring
    0.84
    lible
    0.84
    myk
    0.84
    upport
    0.83
    院校
    0.83
    Activations Density 0.001%

    No Known Activations