© 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. 22-GEMMASCOPE-2-RES-262K
    7. 5575
    Prev
    Next
    INDEX
    Explanations

    mathematical operations with variables

    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_22_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
    m
    0.76
    h
    0.75
    ร้าย
    0.75
    y
    0.71
    s
    0.71
    a
    0.69
    g
    0.68
    usak
    0.67
    t
    0.67
    b
    0.67
    POSITIVE LOGITS
     withd
    0.94
    +
    0.92
     AgNO
    0.87
    '=
    0.86
    =\
    0.86
     गुणनखंड
    0.86
    }=
    0.85
    )}=
    0.85
     pued
    0.84
    }=-
    0.81
    Activations Density 0.132%

    No Known Activations