© 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. 247908
    Prev
    Next
    INDEX
    Explanations

    company providing services or information

    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
    桟
    0.47
     spoonful
    0.47
     denominator
    0.47
     ï
    0.47
    弦
    0.47
    தன
    0.44
    =\
    0.43
    テル
    0.43
    ermos
    0.42
     mềm
    0.41
    POSITIVE LOGITS
    IP
    0.47
     Forma
    0.47
    ajat
    0.46
     forma
    0.46
     පිළිබඳ
    0.46
    unta
    0.46
    ได้รับการ
    0.46
    rea
    0.45
    rasında
    0.45
    es
    0.45
    Activations Density 0.001%

    No Known Activations