© 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
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 3717
    Prev
    Next
    INDEX
    Explanations

    error handling or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    °.
    1.84
    的生活
    1.83
     النار
    1.81
    }.
    1.80
    ין
    1.74
     }.
    1.74
    <bos>
    1.74
     Additionally
    1.74
     Those
    1.73
     },
    1.70
    POSITIVE LOGITS
    -
    1.41
     größte
    0.97
    dfrac
    0.96
    amma
    0.94
     organizer
    0.93
     strategist
    0.93
    ma
    0.91
    -(\
    0.90
     каком
    0.90
    ры
    0.89
    Activations Density 0.018%

    No Known Activations