© 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. 77244
    Prev
    Next
    INDEX
    Explanations

    event, suites, article

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

    what you need

    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
    _{\|
    0.49
    ÜR
    0.43
     найбіль
    0.43
    안
    0.43
     বিশ্বের
    0.42
    역시
    0.42
     возмо
    0.42
    槸
    0.41
    umma
    0.41
    UY
    0.41
    POSITIVE LOGITS
    <code>
    0.54
    سين
    0.51
     premiums
    0.46
     entre
    0.45
     Energie
    0.45
     progres
    0.45
    *
    0.45
     Prentice
    0.44
     refin
    0.44
     daniel
    0.44
    Activations Density 0.000%

    No Known Activations