© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 47974
    Prev
    Next
    INDEX
    Explanations

    Bible versions and translations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anyaan
    0.46
    oribus
    0.43
    nym
    0.42
    cepc
    0.42
    jelasan
    0.41
    exists
    0.41
    薮
    0.41
    dados
    0.41
    ajaran
    0.40
    agonist
    0.40
    POSITIVE LOGITS
     टीम
    0.46
    తా
    0.44
     edged
    0.44
    仕上げ
    0.42
     ICC
    0.41
     새
    0.39
     softens
    0.39
    改
    0.39
     concord
    0.39
     lâ
    0.39
    Activations Density 0.001%

    No Known Activations