© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51777
    Prev
    Next
    INDEX
    Explanations

    core condition block

    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
    孅
    0.42
    筤
    0.42
    媟
    0.42
     Natasha
    0.41
    耔
    0.40
     XXX
    0.40
     Fit
    0.39
    佲
    0.39
    鳧
    0.39
    嚩
    0.39
    POSITIVE LOGITS
    ana
    0.52
    ano
    0.50
     slur
    0.50
    id
    0.46
    ore
    0.45
    ag
    0.43
    ani
    0.43
    ilin
    0.43
    ion
    0.42
    ile
    0.42
    Activations Density 0.007%

    No Known Activations