© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 139198
    Prev
    Next
    INDEX
    Explanations

    words and following tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     godina
    0.47
    },\
    0.45
     खिलाड़ियों
    0.45
    赦
    0.44
     využ
    0.44
    glColor
    0.44
     człon
    0.43
    Λ
    0.43
    tocol
    0.43
    kHz
    0.43
    POSITIVE LOGITS
     себе
    0.46
    ент
    0.45
    ﻪ
    0.45
     Hydro
    0.44
    umnos
    0.43
     ст
    0.43
    হ
    0.42
    спе
    0.42
     непосредственно
    0.42
     CP
    0.41
    Activations Density 0.001%

    No Known Activations