© 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. 181982
    Prev
    Next
    INDEX
    Explanations

    voting in person

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

    brilliantly constructed, reconstruct, maximize

    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
    ร้าง
    0.58
    アカ
    0.54
    ли
    0.50
    นอก
    0.48
    สต
    0.47
    ราง
    0.46
     আরও
    0.46
    ล
    0.45
    राना
    0.45
    ல்
    0.44
    POSITIVE LOGITS
     Wheels
    0.45
     entrop
    0.45
    UCLE
    0.42
     Thermodynamic
    0.42
     Vest
    0.42
     Keeps
    0.42
    Silicon
    0.42
     Christy
    0.42
     സെക്ര
    0.41
    Schemas
    0.41
    Activations Density 0.002%

    No Known Activations