© 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. 157258
    Prev
    Next
    INDEX
    Explanations

    spreading free child need

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

    linkages, marking, classifying, coverage

    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
    immers
    0.44
    叧
    0.41
     Venezuela
    0.40
     உறு
    0.40
    ಟರ್
    0.40
     Stip
    0.40
     Friends
    0.39
    ти
    0.38
     बचाव
    0.38
    icit
    0.38
    POSITIVE LOGITS
    ک
    0.49
     cliquer
    0.49
     czerwca
    0.48
    ཥ
    0.47
     artesan
    0.46
    場所に
    0.45
     denken
    0.45
     scegli
    0.45
    යි
    0.44
    제
    0.44
    Activations Density 0.000%

    No Known Activations