© 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. 83829
    Prev
    Next
    INDEX
    Explanations

    specialist to, Leave a, funds a

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

    friends or parents

    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
    اح
    0.53
     EVERY
    0.48
    イス
    0.47
    د
    0.46
    Th
    0.46
    อนุ
    0.45
    韬
    0.45
    ธ
    0.45
    TECHN
    0.44
    膻
    0.44
    POSITIVE LOGITS
     infringe
    0.48
     close
    0.47
     lowering
    0.45
    vera
    0.45
     নেট
    0.45
     نزدیک
    0.45
     ۸
    0.45
     lowered
    0.44
     ți
    0.44
     fromi
    0.44
    Activations Density 0.000%

    No Known Activations