© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 219226
    Prev
    Next
    INDEX
    Explanations

    laws and sections

    np_acts-logits-general · gemini-2.5-flash-lite

    mix, DSM, developer, drive, sorry, Montessori

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciaux
    0.48
    萎
    0.47
    elijkheid
    0.46
    力量
    0.45
    凭
    0.45
    债券
    0.44
    ます
    0.43
    ون
    0.43
    内核
    0.43
     организаций
    0.42
    POSITIVE LOGITS
     brother
    0.54
    FAN
    0.54
    PEC
    0.52
     restaurant
    0.51
     hatches
    0.51
     තු
    0.51
     hide
    0.50
     soy
    0.50
     commits
    0.50
     mom
    0.49
    Activations Density 0.002%

    No Known Activations