© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3525
    Prev
    Next
    INDEX
    Explanations

    love

    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_16k_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
    ter
    1.92
    ség
    1.49
     Semoga
    1.49
     Proton
    1.38
    ের
    1.37
    Thing
    1.36
    aad
    1.35
    s
    1.34
    ized
    1.33
    ers
    1.32
    POSITIVE LOGITS
    ד
    2.08
    ק
    1.60
    нача
    1.54
    ij
    1.49
    да
    1.49
    轵
    1.45
     sensi
    1.44
    akor
    1.41
     काळात
    1.39
    ைட்
    1.38
    Activations Density 0.092%

    No Known Activations