© 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. 84948
    Prev
    Next
    INDEX
    Explanations

    p.m. or a.m

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

    internal affairs and control

    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
     touchscreen
    0.49
     F
    0.49
     assembly
    0.49
     Assembly
    0.48
    F
    0.48
     T
    0.46
     GT
    0.46
     EHR
    0.45
     MSA
    0.45
    ha
    0.45
    POSITIVE LOGITS
    水の
    0.49
    ផ្
    0.49
    চনায়
    0.48
    лых
    0.46
    水を
    0.46
    ној
    0.45
     ponemos
    0.45
    厠
    0.45
    कॉइन
    0.44
    コーヒー
    0.44
    Activations Density 0.001%

    No Known Activations