© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8041
    Prev
    Next
    INDEX
    Explanations

    phrases separated by periods

    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
    ের
    0.42
    },\
    0.42
    一緒に
    0.40
    Dc
    0.40
    _
    0.39
    s
    0.39
    ̣n
    0.38
    ’
    0.38
    otor
    0.38
     outsiders
    0.38
    POSITIVE LOGITS
     страда
    0.49
    abody
    0.49
     Markle
    0.48
     Wilt
    0.47
     पड़ेगी
    0.47
     stair
    0.46
    ॉर्क
    0.45
     sufrir
    0.45
    fade
    0.44
     NODE
    0.44
    Activations Density 0.112%

    No Known Activations