© 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. 164348
    Prev
    Next
    INDEX
    Explanations

    quotes and delimiters

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

    code delimiters and structure

    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
    testimon
    0.62
    hattim
    0.61
    rapport
    0.60
    YAN
    0.59
    ᆭ
    0.59
    ꫝ
    0.59
     परस्मैपदी
    0.58
    tìm
    0.58
    tetrahydro
    0.57
    𝚅
    0.57
    POSITIVE LOGITS
    ong
    0.73
    ik
    0.73
    ah
    0.65
    ac
    0.64
    og
    0.62
    -
    0.61
    ag
    0.59
    at
    0.59
    ach
    0.58
    ay
    0.55
    Activations Density 0.004%

    No Known Activations