© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 5244
    Prev
    Next
    INDEX
    Explanations

    numbers and ranges

    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
     —
    0.80
     sus
    0.74
     atom
    0.68
    -
    0.68
     krypt
    0.67
     con
    0.67
     balance
    0.67
     –
    0.67
     -
    0.67
     sel
    0.67
    POSITIVE LOGITS
    এর
    1.35
    year
    0.85
    dimensional
    0.82
    calorie
    0.78
    <%=
    0.78
    goers
    0.78
    –
    0.77
    inspired
    0.77
    inizio
    0.76
    Й
    0.75
    Activations Density 0.254%

    No Known Activations