© 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. 52350
    Prev
    Next
    INDEX
    Explanations

    raising £

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

    language and communication

    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
     Raya
    0.46
     Shelley
    0.45
     Strawberry
    0.45
    换
    0.44
     Domingo
    0.43
     Reynolds
    0.42
     Tomato
    0.42
     Equival
    0.42
     Simba
    0.41
    ̂
    0.41
    POSITIVE LOGITS
    鈑
    0.53
     መድሃኒ
    0.49
     médecine
    0.48
    糖尿
    0.47
     polypes
    0.47
     ಔಷ
    0.46
     modellen
    0.46
     ancor
    0.46
     mån
    0.46
    醫
    0.46
    Activations Density 0.000%

    No Known Activations