© 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. 54224
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases and place names

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

    word formation and relationships

    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
    ികി
    0.51
    प्शन
    0.49
     تھے
    0.48
     บอก
    0.47
    志愿
    0.45
    觛
    0.44
    応募
    0.43
    цію
    0.43
    ลล์
    0.43
     дети
    0.42
    POSITIVE LOGITS
     Oeste
    0.51
     OTA
    0.51
     Possession
    0.48
    a
    0.48
     Semiconductors
    0.48
     Alt
    0.47
     Roca
    0.47
     Cardio
    0.47
     Espresso
    0.47
     Johnny
    0.46
    Activations Density 0.000%

    No Known Activations