© 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. 51905
    Prev
    Next
    INDEX
    Explanations

    ghosting, achievement

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

    my interests and passions

    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
    -
    0.48
    ="
    0.45
    =",
    0.42
     einem
    0.41
    p
    0.41
     (
    0.40
     Fitch
    0.40
    =\"
    0.39
     Gründe
    0.38
    的一部分
    0.37
    POSITIVE LOGITS
    leriyle
    0.47
     ACHIEVEMENT
    0.47
    𒉺
    0.47
    ഓം
    0.46
     arba
    0.46
     активности
    0.45
    Celltype
    0.45
    ग्रामीण
    0.45
     اندرو
    0.44
    ﺮ
    0.44
    Activations Density 0.000%

    No Known Activations