© 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. 24571
    Prev
    Next
    INDEX
    Explanations

    cannomen and criminality

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

    structural punctuation and delimiters

    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
     şark
    0.49
    ૫
    0.47
     Adults
    0.46
     Bokeh
    0.46
     bodhis
    0.46
     સ્વા
    0.45
     adulti
    0.45
     પછી
    0.45
    괄
    0.44
     Tottenham
    0.44
    POSITIVE LOGITS
    ل
    0.55
    مة
    0.49
     prins
    0.47
     CRIM
    0.46
    nommen
    0.46
    祿
    0.45
     comandos
    0.44
    riminal
    0.44
     jars
    0.44
    Crim
    0.43
    Activations Density 0.000%

    No Known Activations