© 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. 96890
    Prev
    Next
    INDEX
    Explanations

    can be

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

    ritual circumcision

    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
    𝚋
    0.49
     বয়স
    0.47
     полиции
    0.46
    ススメ
    0.45
     woord
    0.44
     Conseil
    0.43
     cà
    0.43
     présentée
    0.42
     ഭാര്യ
    0.42
     judiciaire
    0.42
    POSITIVE LOGITS
    饗
    0.44
    緞
    0.43
     distillate
    0.43
    inga
    0.42
    icago
    0.40
    Starts
    0.40
    Preparing
    0.40
    Madonna
    0.40
    骷
    0.40
    erved
    0.39
    Activations Density 0.001%

    No Known Activations