© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 168436
    Prev
    Next
    INDEX
    Explanations

    comment on posts

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

    comments on YouTube

    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
    揾
    0.44
     filtro
    0.43
     Hilary
    0.42
    tetra
    0.41
     ತಯ
    0.41
    臨
    0.41
    presas
    0.41
     filtr
    0.40
     ví
    0.39
    濾
    0.39
    POSITIVE LOGITS
     Comment
    0.64
     Comments
    0.64
     comment
    0.61
    评论
    0.57
     댓글
    0.57
     Discussion
    0.55
     commentaire
    0.55
     comments
    0.55
     COMMENT
    0.54
     komentar
    0.54
    Activations Density 0.105%

    No Known Activations