© 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. 203265
    Prev
    Next
    INDEX
    Explanations

    held spell my us his

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

    introduces a new clause

    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
    ImageView
    0.49
    穢
    0.48
     ViewController
    0.45
    ูล
    0.45
    ործ
    0.44
    ✞
    0.44
    鳟
    0.44
    の名
    0.43
    拧
    0.43
    の種類
    0.42
    POSITIVE LOGITS
    kos
    0.50
    kost
    0.49
     assumption
    0.47
     відповіда
    0.46
    keny
    0.45
    isini
    0.44
    kennt
    0.43
     respons
    0.43
    asiswa
    0.42
     assumptions
    0.42
    Activations Density 0.000%

    No Known Activations