© 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. 40256
    Prev
    Next
    INDEX
    Explanations

    political candidate discussions

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

    political candidates and their platforms

    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
     exhale
    0.41
     sov
    0.40
     typ
    0.39
    萎
    0.39
     glo
    0.38
     fallen
    0.38
     ,,
    0.38
    
    0.38
     reactions
    0.38
    ⤷
    0.38
    POSITIVE LOGITS
     후보
    1.05
    Candidate
    1.04
    候选
    1.04
     Candidate
    1.02
     candidacy
    1.02
     उम्मीदवार
    0.97
     kandid
    0.96
    Candidates
    0.96
     candidature
    0.95
     канди
    0.95
    Activations Density 0.098%

    No Known Activations