© 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. 47676
    Prev
    Next
    INDEX
    Explanations

    transactional terms and timeframes

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

    situation assessment

    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
    ZM
    0.46
    _'.$
    0.42
    db
    0.41
    '};
    0.41
    она
    0.40
    Json
    0.40
     हळ
    0.40
    হ
    0.40
     மாறிய
    0.39
    DB
    0.39
    POSITIVE LOGITS
     PayPal
    0.48
    沟通
    0.46
    ถาม
    0.45
    purchase
    0.45
     purchasing
    0.44
     bols
    0.44
     مدت
    0.42
    罄
    0.42
     پاسخ
    0.41
     Purchase
    0.41
    Activations Density 0.000%

    No Known Activations