© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56207
    Prev
    Next
    INDEX
    Explanations

    languages and technical terms

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

    dangerous content or actions

    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
    ’)
    0.50
    ')}
    0.47
     governorship
    0.44
     হাঁট
    0.43
     GPIO
    0.43
     Филип
    0.42
    ’),
    0.41
     £
    0.41
     ज्वाइन
    0.41
    chatroom
    0.39
    POSITIVE LOGITS
     produ
    0.48
     recher
    0.47
     proizv
    0.44
     barbaric
    0.44
    勵
    0.43
     resear
    0.43
     produse
    0.42
    冒险
    0.42
     njega
    0.42
     lange
    0.41
    Activations Density 0.000%

    No Known Activations