© 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. 70485
    Prev
    Next
    INDEX
    Explanations

    estimate the

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

    text or log or sandbox or Alternative

    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
     исходя
    0.57
    isTrack
    0.44
    -//
    0.43
     expressly
    0.43
     Союза
    0.42
     calendário
    0.42
     narrates
    0.42
    mato
    0.42
    рого
    0.41
    getEstado
    0.41
    POSITIVE LOGITS
     SAME
    0.50
     shamb
    0.48
     Great
    0.47
    م
    0.47
     dynam
    0.46
     goo
    0.44
     berl
    0.44
     دش
    0.43
     nærm
    0.43
    という
    0.43
    Activations Density 0.000%

    No Known Activations