© 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. 247335
    Prev
    Next
    INDEX
    Explanations

    academic journal citations

    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
     борь
    0.57
     Professionals
    0.52
    මණ
    0.50
    ３
    0.50
    ℂ
    0.50
    完
    0.49
     міс
    0.48
     कोले
    0.48
     procéder
    0.48
    Ｒ
    0.48
    POSITIVE LOGITS
    rina
    0.49
    ζει
    0.46
    gradient
    0.45
    celle
    0.43
    arus
    0.42
     אר
    0.42
    cel
    0.41
    rus
    0.41
     jä
    0.41
    radi
    0.40
    Activations Density 0.001%

    No Known Activations