© 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. 216707
    Prev
    Next
    INDEX
    Explanations

    KY election fraud

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

    slightly awkward phrases

    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
    十
    0.47
    厝
    0.46
     Temple
    0.42
    五十
    0.41
     FF
    0.39
    Temple
    0.39
    筹
    0.39
    里的
    0.38
    各地
    0.38
     plastered
    0.38
    POSITIVE LOGITS
     échanc
    0.62
    észet
    0.55
     dân
    0.54
    seekbar
    0.54
    रिडोर
    0.54
     informatics
    0.53
     habitants
    0.50
     assurances
    0.50
    데이터
    0.49
     ايه
    0.49
    Activations Density 0.000%

    No Known Activations