© 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. 121000
    Prev
    Next
    INDEX
    Explanations

    concepts or states

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

    skills many don't have

    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
    ؛
    0.54
    ﻦ
    0.46
     decidiu
    0.46
     hiszen
    0.46
    を獲得
    0.44
     prosperous
    0.44
     fez
    0.44
     fizemos
    0.44
    ﻡ
    0.43
     ocorreu
    0.42
    POSITIVE LOGITS
    плом
    0.43
    aranteed
    0.41
     Playhouse
    0.41
    ogan
    0.40
    ankan
    0.40
     επα
    0.40
    Animating
    0.40
     학교
    0.39
    釘
    0.39
    annya
    0.39
    Activations Density 0.004%

    No Known Activations