© 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. 149737
    Prev
    Next
    INDEX
    Explanations

    applications and features

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

    applications and roles

    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
     swears
    0.49
     captivated
    0.47
     massac
    0.47
     sufferings
    0.46
    ラ
    0.46
     soldi
    0.45
     schnell
    0.45
     guter
    0.45
    성은
    0.45
     Trabal
    0.44
    POSITIVE LOGITS
    imper
    0.51
    ại
    0.48
    applications
    0.47
    Ther
    0.46
    s
    0.44
    ąp
    0.42
    昛
    0.42
    Applications
    0.42
    Lin
    0.42
    Transactions
    0.42
    Activations Density 0.001%

    No Known Activations