© 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. 35195
    Prev
    Next
    INDEX
    Explanations

    items or alternatives

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

    connectors and conjunctions

    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
     লাগিলেন
    0.43
     দেখিয়
    0.43
    ளான
    0.42
    AGUE
    0.42
     табы
    0.41
    ד
    0.40
    দিগকে
    0.40
    俟
    0.40
    刽
    0.40
    ை
    0.39
    POSITIVE LOGITS
     किंवा
    0.46
     hoặc
    0.46
     മല
    0.45
     jälkeen
    0.44
    ・
    0.43
    初めて
    0.43
     یا
    0.42
     erstmals
    0.42
     odpad
    0.41
     மற்றும்
    0.41
    Activations Density 0.000%

    No Known Activations