© 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. 154918
    Prev
    Next
    INDEX
    Explanations

    words followed by context

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

    reflexive wedding looking forward obsessed sparking

    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
     Film
    0.51
     hoge
    0.45
     cellules
    0.45
     öff
    0.45
    i
    0.45
     remix
    0.44
    ydd
    0.44
     filme
    0.44
     Remix
    0.44
     Slides
    0.43
    POSITIVE LOGITS
     अनुप
    0.48
    ,=
    0.47
     постанов
    0.46
    ].)
    0.46
    秸
    0.46
    ເວລາ
    0.46
    다는
    0.46
    ảo
    0.45
    [];
    0.44
     అమ
    0.44
    Activations Density 0.001%

    No Known Activations