© 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. 246151
    Prev
    Next
    INDEX
    Explanations

    books or trials

    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
     insoluble
    0.47
    𝑪
    0.44
    WithFieldContext
    0.43
     unbear
    0.42
    お届け
    0.41
    お金
    0.41
     कोय
    0.40
    ിൽ
    0.39
     voorbeeld
    0.39
    ႂ
    0.39
    POSITIVE LOGITS
    тім
    0.46
    '
    0.45
    INTERNAL
    0.40
    ᓵ
    0.40
     caucus
    0.40
    мия
    0.39
    тні
    0.39
    <sub>
    0.38
    ker
    0.38
     potrzeb
    0.38
    Activations Density 0.001%

    No Known Activations