© 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. 12128
    Prev
    Next
    INDEX
    Explanations

    quantities 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
    goài
    0.97
    Immun
    0.87
    Ancest
    0.86
    Ō
    0.84
    <unused1991>
    0.84
    polit
    0.83
    <unused1797>
    0.83
    immune
    0.82
    Medit
    0.81
    Vie
    0.81
    POSITIVE LOGITS
     the
    1.39
     it
    1.21
     this
    1.13
     their
    1.12
    .
    1.11
     a
    1.07
     two
    0.98
     operation
    0.97
     than
    0.96
     but
    0.95
    Activations Density 0.001%

    No Known Activations