© 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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 36039
    Prev
    Next
    INDEX
    Explanations

    sought after

    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
    د
    1.37
    та
    1.34
    ه
    1.34
    യുടെ
    1.28
    e
    1.27
    o
    1.27
    i
    1.20
    એ
    1.18
    യെ
    1.15
    utérus
    1.15
    POSITIVE LOGITS
     coals
    1.15
     but
    1.13
     কিন্তু
    1.11
     and
    1.07
     concisely
    1.06
     But
    1.03
    −−
    1.03
    да
    1.02
     reducing
    1.00
     be
    1.00
    Activations Density 0.000%

    No Known Activations