© 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. 100235
    Prev
    Next
    INDEX
    Explanations

    controllers, single, left, article, job, Ltd

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

    domain availability, name, common, weakness, available, addressing

    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
    鹖
    0.48
    Beef
    0.46
    donation
    0.43
    Feeling
    0.42
    もっと
    0.41
    illed
    0.41
    Pregnant
    0.41
    ιδ
    0.40
    暝
    0.40
     taxe
    0.40
    POSITIVE LOGITS
    on
    0.48
     ช
    0.47
    acken
    0.47
     apabila
    0.46
     penjelasan
    0.46
     összef
    0.45
    ir
    0.45
     umum
    0.45
     optimist
    0.45
    m
    0.45
    Activations Density 0.000%

    No Known Activations