© 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. 41637
    Prev
    Next
    INDEX
    Explanations

    pages, report, institution

    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
    ERY
    1.36
     Conquest
    1.22
    }\,\
    1.20
    不僅
    1.20
    োজন
    1.19
    ない
    1.15
    भाष
    1.15
    aroos
    1.13
    يم
    1.13
     Política
    1.13
    POSITIVE LOGITS
    f
    1.43
    é
    1.42
    m
    1.33
    ir
    1.23
    pital
    1.20
    ic
    1.17
     allant
    1.13
    på
    1.12
    م
    1.09
    ן
    1.09
    Activations Density 0.000%

    No Known Activations