© 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. 115971
    Prev
    Next
    INDEX
    Explanations

    due diligence and availability

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

    API key, analogies

    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
    Inter
    0.49
     οποίος
    0.49
     말미암
    0.49
    UNITED
    0.48
    vip
    0.46
    \
    0.46
     richt
    0.46
     perror
    0.46
     ajutor
    0.45
     rétro
    0.45
    POSITIVE LOGITS
     protesting
    0.46
     Garlic
    0.44
     دارو
    0.43
     institucional
    0.43
    ד
    0.42
    الہ
    0.42
     اکن
    0.42
     ташки
    0.41
    بھی
    0.41
     inaugur
    0.41
    Activations Density 0.000%

    No Known Activations