© 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. 216605
    Prev
    Next
    INDEX
    Explanations

    cost-effective measures, perfect offers, truth told

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

    common ancestor, years, logs, button, cause

    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
     country
    0.45
    ləşdir
    0.44
     Thorn
    0.43
     Banks
    0.41
     consolid
    0.41
    nimmt
    0.41
    ?
    0.41
     Yeni
    0.40
     Weing
    0.40
    ↵
    0.40
    POSITIVE LOGITS
    қ
    0.53
    ్‌
    0.47
    Mga
    0.47
     পরিষ
    0.47
     мог
    0.46
     paediatric
    0.45
     மாண
    0.45
    دی
    0.45
     offenen
    0.44
    Applications
    0.44
    Activations Density 0.001%

    No Known Activations