© 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. 241694
    Prev
    Next
    INDEX
    Explanations

    and going

    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
    タオル
    0.46
    MARINE
    0.43
    ത്യാ
    0.42
    兩
    0.41
    ില
    0.40
    漫畫
    0.40
    माल
    0.40
    られる
    0.40
    若干
    0.40
     blanchâtre
    0.40
    POSITIVE LOGITS
     packs
    0.46
     fake
    0.46
     ২০২১
    0.45
    ners
    0.45
     _{
    0.45
     ২০২২
    0.44
    slot
    0.43
    tele
    0.43
    thon
    0.42
     _{\
    0.41
    Activations Density 0.000%

    No Known Activations