© 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. 191590
    Prev
    Next
    INDEX
    Explanations

    countries, brands, or specific entities

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

    intense desire and extreme actions

    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
    <0xB3>
    0.47
     पनि
    0.44
    вів
    0.43
     fortfarande
    0.43
     Similarly
    0.43
    ђе
    0.43
    こともある
    0.42
    geg
    0.42
    也非常
    0.42
    薦
    0.41
    POSITIVE LOGITS
    ডো
    0.57
     atuação
    0.50
     poprzez
    0.48
     estrategia
    0.48
     dissection
    0.47
     potrzeb
    0.47
     doctrina
    0.46
    通过
    0.46
     utilização
    0.46
     estética
    0.46
    Activations Density 0.000%

    No Known Activations