© 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. 172322
    Prev
    Next
    INDEX
    Explanations

    documents issued

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

    technical and list structure

    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
    Debut
    0.53
    㤟
    0.52
    <unused736>
    0.51
    <unused330>
    0.49
     इंद
    0.48
    AW
    0.48
    Fav
    0.48
     \{\
    0.47
    ">(</
    0.47
     कृपा
    0.47
    POSITIVE LOGITS
     circula
    0.47
    ionati
    0.46
     inference
    0.45
    ುತ್ತದೆ
    0.45
     passi
    0.44
    rical
    0.44
     înce
    0.44
     binary
    0.44
     generali
    0.44
    ری
    0.43
    Activations Density 0.000%

    No Known Activations