© 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. 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-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
    ের
    0.43
    },\
    0.42
    ’
    0.41
    ̣n
    0.40
    Dc
    0.40
     outsiders
    0.39
    _
    0.39
    s
    0.39
    ị
    0.39
    otor
    0.38
    POSITIVE LOGITS
    abody
    0.48
     Markle
    0.48
    ॉर्क
    0.47
     страда
    0.46
     stair
    0.46
     skillset
    0.46
     Wilt
    0.45
    يف
    0.45
     マーク
    0.44
    fade
    0.44
    Activations Density 0.000%

    No Known Activations