© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93357
    Prev
    Next
    INDEX
    Explanations

    code snippets and descriptive phrases

    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
     with
    -0.96
     began
    -0.90
     moved
    -0.89
     started
    -0.88
    旋
    -0.87
     begins
    -0.86
     highlighting
    -0.85
     came
    -0.84
     Despite
    -0.81
     despite
    -0.81
    POSITIVE LOGITS
     douze
    0.91
     alté
    0.91
     élar
    0.90
     emporter
    0.89
     occuper
    0.88
     échanti
    0.88
    ひた
    0.85
     panneaux
    0.85
     スリーブ
    0.84
    Objekt
    0.84
    Activations Density 0.000%

    No Known Activations