© 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. 61556
    Prev
    Next
    INDEX
    Explanations

    save this

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

    Gathering credentials

    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
    ales
    0.44
    t
    0.43
     maintained
    0.43
    Y
    0.43
     नर्मदा
    0.43
     otev
    0.42
    icit
    0.42
    и
    0.41
    V
    0.41
    ah
    0.41
    POSITIVE LOGITS
     unintended
    0.49
     στις
    0.47
     випад
    0.47
     modifiers
    0.47
    namefont
    0.47
     জঙ্গি
    0.46
     мають
    0.46
    ളുടെ
    0.46
     Unterstützung
    0.45
    有两种
    0.45
    Activations Density 0.000%

    No Known Activations