© 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. 10300
    Prev
    Next
    INDEX
    Explanations

    cravings and version

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

    granting exclusive rights to creators

    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
    ItemStack
    0.50
     ইল
    0.47
     อาจ
    0.44
     більш
    0.44
    訕
    0.44
    ியுள்ளது
    0.42
    த்தினை
    0.42
    耦
    0.42
     Пі
    0.41
     khá
    0.41
    POSITIVE LOGITS
    fony
    0.43
    용
    0.41
    (=
    0.41
     parabola
    0.41
    =
    0.41
    T
    0.40
    곱
    0.40
     सुविधा
    0.40
    uaire
    0.38
    ಗೋ
    0.38
    Activations Density 0.000%

    No Known Activations