© 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. 33298
    Prev
    Next
    INDEX
    Explanations

    a less, oh gosh

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

    symbols and punctuation marks

    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
     emanating
    0.51
     using
    0.51
     propagand
    0.45
     planted
    0.44
     ['
    0.44
     propaganda
    0.44
     pervasive
    0.44
     planting
    0.43
     created
    0.42
    :[
    0.42
    POSITIVE LOGITS
    మ్యాచ్
    0.57
    鋅
    0.56
     شرطونه
    0.52
     अमाउंट
    0.52
    谦
    0.50
    比赛
    0.48
     જિલ્
    0.48
     ओलंपिक
    0.48
     உயரம்
    0.48
     구간
    0.48
    Activations Density 0.000%

    No Known Activations