© 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. 4717
    Prev
    Next
    INDEX
    Explanations

    list and bullet point structure

    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
    senior
    1.36
    v
    1.35
    chief
    1.34
    V
    1.32
    aps
    1.28
     evidence
    1.26
    Member
    1.24
    turn
    1.24
    tracer
    1.23
    onc
    1.19
    POSITIVE LOGITS
    edk
    2.03
    icina
    2.03
    gleichen
    1.98
    ppermint
    1.94
    iencia
    1.91
    adayo
    1.88
    า
    1.87
    ()">
    1.86
    uct
    1.85
    ='"+
    1.84
    Activations Density 0.012%

    No Known Activations