© 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. 59340
    Prev
    Next
    INDEX
    Explanations

    updates and changes

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

    free entry

    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
    िन
    0.55
    ན
    0.51
    N
    0.49
    carpet
    0.45
    although
    0.43
    夾
    0.43
    चालित
    0.42
    chicken
    0.42
    chromed
    0.41
     N
    0.41
    POSITIVE LOGITS
     변화
    0.67
     actualizar
    0.50
    <unused48>
    0.49
     dữ
    0.48
     přid
    0.47
     aggior
    0.47
     funzionalità
    0.46
     گرفت
    0.46
     vasocon
    0.46
     מער
    0.46
    Activations Density 0.000%

    No Known Activations