© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3689
    Prev
    Next
    INDEX
    Explanations

    on behalf of

    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
    鹉
    1.85
    ព
    1.55
     tract
    1.54
     przyp
    1.51
    ing
    1.51
     hem
    1.50
     hand
    1.48
    спонд
    1.47
     cent
    1.47
     method
    1.46
    POSITIVE LOGITS
    ʒ
    2.43
    ifference
    2.36
    riving
    2.31
    owntown
    2.18
    iamond
    2.17
    ependence
    2.15
    etection
    2.11
    irectional
    2.09
    ramatic
    2.08
    悸
    2.08
    Activations Density 0.183%

    No Known Activations