© 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. 136606
    Prev
    Next
    INDEX
    Explanations

    good you're asking

    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
    tų
    0.52
    uvieron
    0.47
    burgo
    0.46
    (-
    0.45
    ons
    0.45
    uced
    0.44
     丸
    0.42
    ुस्तान
    0.42
     pl
    0.41
    oncer
    0.41
    POSITIVE LOGITS
    િજા
    0.54
    對方
    0.43
     Lef
    0.41
     Districts
    0.40
     LWR
    0.39
     sempre
    0.39
    对方
    0.38
     always
    0.38
    डर
    0.38
    弱
    0.38
    Activations Density 0.002%

    No Known Activations