© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 10424
    Prev
    Next
    INDEX
    Explanations

    ever or never

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     sympathize
    1.61
    ة
    1.59
    ون
    1.48
     oxidize
    1.35
    س
    1.33
     criticize
    1.31
    niejs
    1.30
    ни
    1.29
    व्ह
    1.24
     neutralize
    1.23
    POSITIVE LOGITS
     a
    1.76
     an
    1.76
     it
    1.55
    ל
    1.50
     Never
    1.48
    C
    1.45
     the
    1.38
    O
    1.38
    К
    1.32
    S
    1.31
    Activations Density 0.050%

    No Known Activations