© 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. 109387
    Prev
    Next
    INDEX
    Explanations

    presenting or introducing

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

    we present / this paper presents

    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
    ilin
    0.49
    í
    0.48
    apad
    0.47
    ivir
    0.46
    ollen
    0.46
    imet
    0.45
    ivi
    0.44
    iene
    0.44
    ieu
    0.43
    ieg
    0.43
    POSITIVE LOGITS
    އ
    0.55
     Bül
    0.54
    onasera
    0.52
     Candles
    0.51
     strolled
    0.51
    ﮐ
    0.51
    ガネ
    0.50
     worry
    0.49
     motorbike
    0.49
     corresponded
    0.48
    Activations Density 0.000%

    No Known Activations