© 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. 116139
    Prev
    Next
    INDEX
    Explanations

    costly cleaners

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

    "`servant whom", "language games", "overlord statues`

    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
     jendela
    0.53
    嗮
    0.47
     explotación
    0.45
     perfetta
    0.45
     Asociación
    0.45
     estatura
    0.45
     perfeita
    0.45
     солнца
    0.45
    蟬
    0.45
     світу
    0.45
    POSITIVE LOGITS
     FODC
    0.51
    ης
    0.45
     renamed
    0.45
    ব্যাপী
    0.44
    '\
    0.44
    prepend
    0.43
    .`);
    0.42
     Bali
    0.42
     UNF
    0.42
    Root
    0.41
    Activations Density 0.000%

    No Known Activations