© 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. 64859
    Prev
    Next
    INDEX
    Explanations

    speaking in diverse tongues

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

    white genocide

    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
    ير
    0.49
     primero
    0.47
     piensan
    0.47
    としては
    0.46
    0
    0.46
    ﻓ
    0.45
     histórica
    0.44
    籐
    0.44
     strane
    0.44
     සි
    0.43
    POSITIVE LOGITS
    s
    0.58
     Imped
    0.55
    es
    0.55
    äude
    0.54
     Humidity
    0.53
    ing
    0.52
    cadilly
    0.50
    swürdig
    0.50
     Shouldn
    0.49
     Highlighter
    0.49
    Activations Density 0.000%

    No Known Activations