© 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. 219241
    Prev
    Next
    INDEX
    Explanations

    legal and business concepts

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

    volunteering supporters

    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
     Election
    0.53
    END
    0.52
     July
    0.51
     Emergency
    0.48
     Allow
    0.48
     y
    0.47
     election
    0.47
     Optional
    0.47
     e
    0.47
     ouverture
    0.46
    POSITIVE LOGITS
     персонала
    0.45
    一面
    0.44
     supporters
    0.43
     كبيرة
    0.43
    跖
    0.42
     вони
    0.41
    supporters
    0.41
     şekilde
    0.40
     deplete
    0.40
     rattled
    0.40
    Activations Density 0.001%

    No Known Activations