© 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. 87519
    Prev
    Next
    INDEX
    Explanations

    Construction sector and industry specifics

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

    captures routed customers

    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
    tag
    0.52
    tower
    0.48
     गणतंत्र
    0.48
    </strong>
    0.46
     تک
    0.46
     ιστο
    0.46
    histogram
    0.46
    is
    0.45
    equals
    0.45
     সহ
    0.45
    POSITIVE LOGITS
    XD
    0.49
    🥤
    0.46
    TRR
    0.46
    ేష్
    0.45
    Gui
    0.44
    ETA
    0.44
     изменя
    0.43
    Ud
    0.42
    LDL
    0.41
    Penumpang
    0.41
    Activations Density 0.001%

    No Known Activations