© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 36722
    Prev
    Next
    INDEX
    Explanations

    representing tables, arched bridge, fairly tail, stretched country, undirected relationships

    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
    این
    1.23
    ن
    1.06
    يك
    1.03
    วัส
    1.03
     비해
    1.01
    IK
    0.96
    问题
    0.95
     еди
    0.94
     mots
    0.94
    椹
    0.93
    POSITIVE LOGITS
    д
    1.17
    de
    1.07
    ther
    1.06
    lerin
    1.06
     đỡ
    1.06
    lessness
    1.05
     arada
    1.04
    lerden
    1.02
    िणी
    1.02
    llllll
    0.99
    Activations Density 0.000%

    No Known Activations