© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 57001
    Prev
    Next
    INDEX
    Explanations

    at least one of the following

    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
     sandpaper
    0.61
     cak
    0.57
     temperatur
    0.54
     ć
    0.53
     HCP
    0.52
     fecal
    0.52
     terb
    0.51
     fec
    0.51
     Brides
    0.51
     ∠
    0.50
    POSITIVE LOGITS
    OVER
    0.53
    MILL
    0.51
    n
    0.49
    ENTIAL
    0.48
    Compilation
    0.48
    Ent
    0.47
    Austral
    0.47
    Endian
    0.47
    PAN
    0.46
    AMES
    0.46
    Activations Density 0.003%

    No Known Activations