© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21933
    Prev
    Next
    INDEX
    Explanations

    new car gadgets

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

    life is too short

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    0.52
    ०
    0.47
    ige
    0.45
    ции
    0.45
     Suez
    0.45
    de
    0.45
                
    0.44
    Доб
    0.44
    に
    0.44
    だ
    0.44
    POSITIVE LOGITS
    Uppercase
    0.47
    onasera
    0.47
    🩰
    0.46
     granddaughters
    0.46
    advertising
    0.45
     بیوی
    0.45
    composable
    0.45
     ragazze
    0.43
    ᚕ
    0.43
    otto
    0.43
    Activations Density 0.000%

    No Known Activations