© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20020
    Prev
    Next
    INDEX
    Explanations

    flag indicates, payments made, stopping by

    np_acts-logits-general · gemini-2.5-flash-lite

    respond to prompts with specific information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SG
    0.54
    קל
    0.52
    s
    0.51
    Curl
    0.50
    Town
    0.50
    Aren
    0.50
    1
    0.50
     Curl
    0.49
    Partner
    0.49
    Tour
    0.48
    POSITIVE LOGITS
    섦
    0.56
     вста
    0.50
     vestib
    0.48
     BMC
    0.48
     lichaam
    0.47
    નિક
    0.46
     NIC
    0.46
     manhood
    0.45
     subside
    0.45
     vertebra
    0.45
    Activations Density 0.000%

    No Known Activations