© 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. 141677
    Prev
    Next
    INDEX
    Explanations

    safety rules, always supporting, cancer immunity

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

    legislation or upheld

    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
     larva
    0.52
    ش
    0.52
     forest
    0.48
     fieldValue
    0.47
     pregnant
    0.47
     humid
    0.47
     harassed
    0.47
     carpenter
    0.46
     hill
    0.46
     riverside
    0.46
    POSITIVE LOGITS
    withtag
    0.51
     теор
    0.50
    襁
    0.48
    JPN
    0.48
    祐
    0.46
    wurf
    0.46
    ್ರಿ
    0.46
     दुसरी
    0.46
    䈉
    0.45
    䡓
    0.45
    Activations Density 0.000%

    No Known Activations