© 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. 17095
    Prev
    Next
    INDEX
    Explanations

    error, loss, momentum, update

    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
     ήταν
    0.47
     Зараз
    0.44
     כש
    0.43
    abelian
    0.42
    طلاب
    0.41
    色は
    0.41
    𓂃
    0.41
    войства
    0.41
    iyon
    0.41
     মাননীয়
    0.41
    POSITIVE LOGITS
    ,
    0.50
    );
    0.46
     demi
    0.46
    8
    0.46
     triggered
    0.44
    1
    0.44
     acupuncture
    0.43
     such
    0.42
    UR
    0.42
    2
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.