© 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. 102638
    Prev
    Next
    INDEX
    Explanations

    enough size erosion

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

    even if

    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
    agation
    0.53
    ⾼
    0.47
    ures
    0.47
    ldes
    0.46
     使っ
    0.45
     фир
    0.43
     Кі
    0.43
    ishing
    0.42
     jede
    0.42
     Cdc
    0.42
    POSITIVE LOGITS
     ruso
    0.48
     symbolName
    0.47
    гистра
    0.44
    dokka
    0.42
    snackbar
    0.42
    忌
    0.42
     filtered
    0.41
     cerr
    0.41
     mensagem
    0.41
     textured
    0.41
    Activations Density 0.000%

    No Known Activations