© 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. 22-GEMMASCOPE-RES-131K
    7. 15817
    Prev
    Next
    INDEX
    Explanations

    technical or multilingual content

    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
     каждом
    -1.13
     münchen
    -1.04
    Quién
    -1.02
     parlano
    -1.02
     аккумулятор
    -1.01
     prestazioni
    -0.95
    また
    -0.95
     contatto
    -0.92
     dalších
    -0.90
     Entdecke
    -0.88
    POSITIVE LOGITS
    sugges
    0.97
     zusammenge
    0.93
    基本的
    0.92
     Apro
    0.91
    регистри
    0.90
    Angleterre
    0.90
    engibre
    0.89
     cuantas
    0.88
    关卡
    0.88
     pede
    0.88
    Activations Density 0.000%

    No Known Activations