© 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. 10306
    Prev
    Next
    INDEX
    Explanations

    `@@ROWCOUNT`, `FETCH`, `RUN`, `extension`, `strategy`, `hunter`

    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
    acking
    1.21
    é
    1.16
    '
    1.13
    ]
    1.13
    our
    1.11
    .,
    1.11
    >
    1.11
    ographic
    1.09
    aging
    1.09
    ang
    1.08
    POSITIVE LOGITS
     calculi
    1.34
    िकुलम
    1.21
     tenths
    1.20
     dvara
    1.19
    КО
    1.16
     glycolysis
    1.16
     dobl
    1.15
     conifers
    1.14
    𝐜
    1.14
    measuredangle
    1.13
    Activations Density 0.000%

    No Known Activations