© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47551
    Prev
    Next
    INDEX
    Explanations

    option higher

    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
    በ
    0.46
     an
    0.44
    3
    0.44
    eler
    0.43
    larla
    0.43
    astien
    0.43
    he
    0.41
    ofed
    0.41
    合
    0.41
    র্প
    0.40
    POSITIVE LOGITS
     catalase
    0.45
     ensures
    0.45
     exceeds
    0.45
    specifiedByURL
    0.45
     vocab
    0.45
     undermines
    0.45
    いくつ
    0.44
     sélectionnés
    0.44
     engages
    0.43
     Begriff
    0.43
    Activations Density 0.000%

    No Known Activations