© 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. 203735
    Prev
    Next
    INDEX
    Explanations

    numbers following words like 'twelve' or preceding 'months'

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

    limited or specific contexts

    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
     될
    0.49
    謎
    0.49
    입니다
    0.46
     SOME
    0.45
     це
    0.45
     오브
    0.45
     ಅದು
    0.44
     ਡ
    0.43
    ᄁ
    0.43
    ższy
    0.43
    POSITIVE LOGITS
     picket
    0.43
     person
    0.43
     Pap
    0.43
     distributor
    0.42
     Belle
    0.41
     canonical
    0.41
     chaperone
    0.41
     tailor
    0.41
     prune
    0.40
     mengadakan
    0.40
    Activations Density 0.005%

    No Known Activations