© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2656
    Prev
    Next
    INDEX
    Explanations

    handling requests and permissions

    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
    Councillor
    2.03
    }}=(
    2.00
    様子
    1.90
     Tukey
    1.89
    ジュニア
    1.89
    ريقة
    1.86
    GORITHM
    1.83
    )}=\
    1.83
     Cllr
    1.82
    ynos
    1.82
    POSITIVE LOGITS
    books
    1.70
    genre
    1.69
     поча
    1.67
    mix
    1.57
    touch
    1.48
    resonant
    1.48
     жан
    1.48
    cap
    1.47
    base
    1.46
    imper
    1.45
    Activations Density 0.287%

    No Known Activations