© 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. 35156
    Prev
    Next
    INDEX
    Explanations

    SIAA, peer review, treadmill, Doctors, fan

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

    concerns about size, infidelity, gut feelings

    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
     ble
    0.44
     ولي
    0.41
     Vide
    0.41
     Не
    0.40
     έγ
    0.40
     Nachricht
    0.40
     b
    0.40
     explan
    0.40
     basi
    0.39
     když
    0.39
    POSITIVE LOGITS
     padassa
    0.45
    bikes
    0.44
    。
    0.44
    犢
    0.44
    粉丝
    0.43
    ەم
    0.43
    粉絲
    0.42
    她的
    0.42
     BELOW
    0.42
    Below
    0.42
    Activations Density 0.000%

    No Known Activations