© 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. 10653
    Prev
    Next
    INDEX
    Explanations

    variables like `I`, `R`, `B`, `T`, `m`, `a`, `r`, `min`, `avg`, `s`, `t`, `ij`, `Hg`

    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
    DR
    1.73
    OFF
    1.56
    and
    1.53
    staking
    1.49
    एस
    1.48
    ৮
    1.48
    了一个
    1.47
    SOLD
    1.47
    8
    1.45
     and
    1.45
    POSITIVE LOGITS
     Execution
    1.46
    יים
    1.44
     Retrieval
    1.44
     Asa
    1.34
     BP
    1.33
     Verification
    1.33
     reactants
    1.30
    nsics
    1.30
     Utilization
    1.27
     Bcl
    1.27
    Activations Density 0.017%

    No Known Activations