© 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. 34518
    Prev
    Next
    INDEX
    Explanations

    new players enjoy

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

    first-time visitor

    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
    త్తి
    0.43
     failures
    0.38
    采
    0.38
    MLL
    0.37
     interruption
    0.37
     alteration
    0.37
    idental
    0.36
    Failed
    0.36
     Deter
    0.36
    ForegroundColor
    0.36
    POSITIVE LOGITS
     બાદ
    0.49
    arki
    0.48
     പ്രത്യേക
    0.48
    aw
    0.47
     kuna
    0.47
     കൂടുതല്‍
    0.46
    ၃
    0.45
     मग
    0.45
     Nhà
    0.45
     kajian
    0.45
    Activations Density 0.001%

    No Known Activations