© 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. 195584
    Prev
    Next
    INDEX
    Explanations

    location names and specific entities

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

    gather data

    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
     pekan
    0.48
    ське
    0.48
     outre
    0.47
    चार्ज
    0.46
    तोष
    0.46
    ڑے
    0.46
    لم
    0.44
    🦌
    0.44
    ä
    0.43
     bane
    0.43
    POSITIVE LOGITS
    return
    0.49
    responsibility
    0.48
    without
    0.48
     অস্ট্র
    0.47
    except
    0.46
     asignar
    0.46
    dateTimePicker
    0.45
    assertEqual
    0.44
    Ala
    0.44
    +-
    0.44
    Activations Density 0.000%

    No Known Activations