© 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. 47721
    Prev
    Next
    INDEX
    Explanations

    profanity and insults

    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
     Adder
    0.49
     "$
    0.49
    adic
    0.47
    PointXYZ
    0.42
    Adder
    0.42
     X
    0.42
    Add
    0.41
    واس
    0.41
    adder
    0.41
     Add
    0.40
    POSITIVE LOGITS
     multidiscipl
    0.54
    疾患
    0.49
     questões
    0.49
     entornos
    0.49
     contexte
    0.48
    の関係
    0.48
    産
    0.47
    コーディ
    0.47
     processos
    0.46
    दायी
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.