© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 220224
    Prev
    Next
    INDEX
    Explanations

    research and writing context

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

    factual inaccuracies

    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
    //
    0.48
     pulses
    0.47
     tokens
    0.47
     regs
    0.46
     NPs
    0.44
     supple
    0.44
    6
    0.44
     NPR
    0.43
    ußen
    0.43
     bords
    0.42
    POSITIVE LOGITS
    ן
    0.57
    仼
    0.55
     വിൽപ്പന
    0.52
     desplazamiento
    0.52
    ските
    0.51
     ক্রয়
    0.51
    leyici
    0.50
    राइ
    0.50
     protezione
    0.49
     egyes
    0.49
    Activations Density 0.000%

    No Known Activations