© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10877
    Prev
    Next
    INDEX
    Explanations

    Q followed by punctuation or specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    которые
    2.00
    THING
    1.83
    ಾ
    1.66
    ductory
    1.66
    ので
    1.63
    ங்கிணை
    1.60
    at
    1.58
    spaper
    1.55
    ী
    1.50
    ad
    1.49
    POSITIVE LOGITS
    cknowled
    2.37
    s
    2.15
    ्स
    1.96
    ের
    1.85
    sd
    1.82
    tf
    1.81
    sı
    1.81
    ્સ
    1.70
    schol
    1.68
    si
    1.68
    Activations Density 0.008%

    No Known Activations