© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 135121
    Prev
    Next
    INDEX
    Explanations

    UI component rendering

    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
     can
    0.57
    i
    0.56
    alf
    0.55
    ati
    0.53
    cart
    0.53
     charges
    0.53
    j
    0.52
    q
    0.52
    ด้วย
    0.51
     ques
    0.51
    POSITIVE LOGITS
     kracht
    0.49
    提到
    0.44
    ленном
    0.43
     columnas
    0.43
    sterreich
    0.42
    ﺌ
    0.42
    mlich
    0.41
    ولا
    0.41
     noticia
    0.41
    وع
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.