© 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. 81521
    Prev
    Next
    INDEX
    Explanations

    after `now`

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

    incredibly valuable, their inability

    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
    OCA
    0.45
    uities
    0.44
     exercising
    0.43
    OG
    0.43
     deliberation
    0.43
     DOM
    0.42
     exercise
    0.42
    <0x80>
    0.42
     wonderful
    0.41
     certificate
    0.40
    POSITIVE LOGITS
     ойнотуу
    0.58
     spieg
    0.55
     incluidas
    0.55
     reprez
    0.55
     knelt
    0.54
     армии
    0.53
     incarn
    0.53
    SwapChain
    0.52
     drap
    0.52
    Ἠ
    0.51
    Activations Density 0.000%

    No Known Activations