© 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. 220722
    Prev
    Next
    INDEX
    Explanations

    may use

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

    spending, control, refill

    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
     スター
    0.49
    ou
    0.49
    ohid
    0.48
    দেশীয়
    0.48
     sowohl
    0.47
     amassed
    0.46
    ig
    0.45
    Ų
    0.45
    ajou
    0.45
    esha
    0.45
    POSITIVE LOGITS
    쐞
    0.45
     должен
    0.45
     يجب
    0.43
    ต้อง
    0.41
     downwards
    0.41
    そらく
    0.40
     должна
    0.40
    鬨
    0.39
    べき
    0.39
    ད་
    0.39
    Activations Density 0.001%

    No Known Activations