© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76141
    Prev
    Next
    INDEX
    Explanations

    language identification and conditionals

    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
    in
    0.60
    e
    0.50
    ed
    0.49
    right
    0.47
    u
    0.46
    er
    0.45
    re
    0.45
    i
    0.44
    ar
    0.43
     but
    0.43
    POSITIVE LOGITS
     Auswirkungen
    0.56
     Cenomanian
    0.54
     ഗവേഷ
    0.53
     பரு
    0.51
     zusätzlichen
    0.50
     Lernen
    0.49
     murderous
    0.48
    的游戏
    0.47
    有助于
    0.47
    Methylsulfanyl
    0.47
    Activations Density 0.007%

    No Known Activations