© 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-16K
    7. 12559
    Prev
    Next
    INDEX
    Explanations

    requesting or needing something

    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
    ла
    2.17
    е
    2.05
    臾
    1.99
    ל
    1.96
    ра
    1.84
    п
    1.78
     وفي
    1.71
    ro
    1.70
    ক্স
    1.70
    вається
    1.63
    POSITIVE LOGITS
    }
    2.16
    螓
    1.55
    】，
    1.54
     coûts
    1.53
    >
    1.46
    corruption
    1.45
    pK
    1.45
     ώστε
    1.44
    }'],
    1.44
    韆
    1.44
    Activations Density 0.227%

    No Known Activations