© 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. 86583
    Prev
    Next
    INDEX
    Explanations

    compatible with

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

    section enumeration

    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
     cati
    0.47
     cation
    0.45
     °,
    0.45
    InnerHTML
    0.43
     ஆசிரியர்
    0.43
    敚
    0.43
     quenched
    0.42
     ɖ
    0.42
    行
    0.42
    ensely
    0.42
    POSITIVE LOGITS
    rid
    0.50
     Kasper
    0.46
    araf
    0.43
    getSession
    0.43
    nil
    0.42
    kill
    0.42
    rę
    0.42
    ignore
    0.41
    wani
    0.41
    koľ
    0.41
    Activations Density 0.000%

    No Known Activations