© 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. 150616
    Prev
    Next
    INDEX
    Explanations

    time, events, and conditions

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

    following common phrases

    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
     as
    0.53
     wir
    0.46
    ا
    0.46
     ory
    0.44
    Bir
    0.43
    They
    0.43
    Login
    0.42
    ض
    0.42
     with
    0.42
     catar
    0.42
    POSITIVE LOGITS
    事业单位
    0.52
    erequisite
    0.50
    骛
    0.49
    द्रोह
    0.48
    歧
    0.47
    volve
    0.46
    墻
    0.46
    containsKey
    0.46
     აღმასრულებელი
    0.45
    interesse
    0.44
    Activations Density 0.000%

    No Known Activations