© 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. 205062
    Prev
    Next
    INDEX
    Explanations

    initially hidden

    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
    Depth
    0.55
    Leaf
    0.52
    Entry
    0.47
    antile
    0.47
    depth
    0.47
    Park
    0.46
     Dragonfly
    0.45
    ଁ
    0.45
     damping
    0.44
    🎋
    0.44
    POSITIVE LOGITS
     resultado
    0.55
     Muslims
    0.51
     whipped
    0.50
     jah
    0.48
     representante
    0.46
     케
    0.46
     mutta
    0.45
     innan
    0.45
     muita
    0.44
     sebelum
    0.43
    Activations Density 0.004%

    No Known Activations