© 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. 225895
    Prev
    Next
    INDEX
    Explanations

    writing or indicating position

    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
    ต
    0.55
    햇
    0.52
    Ма
    0.49
     үч
    0.48
    ᴏ
    0.48
    할
    0.47
    পত
    0.47
    Ло
    0.47
    ᚕ
    0.47
    সময়
    0.47
    POSITIVE LOGITS
     escrib
    0.53
    டுகள்
    0.53
     hon
    0.47
     alph
    0.47
     Pied
    0.44
     anybody
    0.42
     compute
    0.42
     Glaub
    0.41
     porque
    0.40
    isex
    0.40
    Activations Density 0.000%

    No Known Activations