© 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. 88804
    Prev
    Next
    INDEX
    Explanations

    that youfamily to call you on

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

    age, adolescence, self, hoping to

    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
    да
    0.44
    人
    0.43
    כ
    0.43
    人了
    0.43
    asty
    0.42
    썹
    0.42
    ಜ್ಯ
    0.41
    Exit
    0.41
    蕾
    0.41
    ilt
    0.40
    POSITIVE LOGITS
     niektó
    0.59
     Chac
    0.57
     Overwatch
    0.56
     Prim
    0.55
     precisión
    0.55
     Tüm
    0.55
     Foli
    0.55
     Vag
    0.54
     millilit
    0.53
     Hua
    0.53
    Activations Density 0.001%

    No Known Activations