© 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. 196656
    Prev
    Next
    INDEX
    Explanations

    games for all ages

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

    theme park

    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
    लेटर
    0.46
     unbreakable
    0.46
    енча
    0.46
    惠
    0.46
    لوث
    0.45
    0.45
    colorControl
    0.45
    ετε
    0.45
     Chung
    0.44
    只需
    0.44
    POSITIVE LOGITS
     сі
    0.47
     அடிக்க
    0.47
     опа
    0.46
     публі
    0.46
     CIRCU
    0.45
     pourtant
    0.45
    Many
    0.43
    ■
    0.42
    CL
    0.42
     reparation
    0.42
    Activations Density 0.000%

    No Known Activations