© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2987
    Prev
    Next
    INDEX
    Explanations

    action verbs followed by completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    <
    0.41
    াইজ
    0.38
     Wang
    0.36
     Operand
    0.35
    krb
    0.35
     décrites
    0.35
    pragma
    0.34
    import
    0.34
    瀵
    0.33
     <
    0.32
    POSITIVE LOGITS
     offs
    0.66
    ings
    0.59
    backs
    0.57
    able
    0.55
    downs
    0.52
    iness
    0.52
    outs
    0.51
    athons
    0.50
    ers
    0.50
     downs
    0.48
    Activations Density 0.193%

    No Known Activations