© 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. 158925
    Prev
    Next
    INDEX
    Explanations

    voltage, cheese, name

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

    negative connotations and conflict

    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
    ీ
    0.46
    ayette
    0.46
    কাম
    0.45
     страхо
    0.44
     आरोग्य
    0.42
    гова
    0.42
     tổ
    0.42
    িয়াছি
    0.42
     উত্তম
    0.42
     સામ
    0.42
    POSITIVE LOGITS
    種類の
    0.46
    頻
    0.45
    値段
    0.45
    льнай
    0.44
    adrenaline
    0.44
    ジュニア
    0.44
    ahydro
    0.43
     grandiose
    0.43
    وة
    0.42
    colorful
    0.42
    Activations Density 0.000%

    No Known Activations