© 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. 199968
    Prev
    Next
    INDEX
    Explanations

    drawing near

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

    contributing to shield

    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
    am
    0.47
    Support
    0.46
     ??
    0.46
    VERTISEMENT
    0.45
    ت
    0.45
    NIE
    0.44
    LAW
    0.44
    \\
    0.43
     vínculos
    0.42
    ai
    0.41
    POSITIVE LOGITS
    achadh
    0.53
    უნქ
    0.49
    鹖
    0.48
    änge
    0.47
    તાઓ
    0.47
    లోకి
    0.45
     Spacious
    0.45
    㭂
    0.44
    abhave
    0.43
     GameManager
    0.43
    Activations Density 0.001%

    No Known Activations