© 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. 105769
    Prev
    Next
    INDEX
    Explanations

    following specific contrast words

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

    technical functions and foreign words

    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
    ガ
    0.48
     반지
    0.46
    混沌
    0.45
    胯
    0.44
     புராண
    0.43
    पि
    0.43
    飞行
    0.43
     moonlight
    0.42
    石
    0.42
     langsam
    0.42
    POSITIVE LOGITS
    specified
    0.44
    ResponseEntity
    0.44
    sub
    0.42
    bundle
    0.41
     établissement
    0.40
     doubleheader
    0.40
    ził
    0.40
    girlfriend
    0.39
    তনের
    0.39
    য্
    0.39
    Activations Density 0.001%

    No Known Activations