© 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. 36216
    Prev
    Next
    INDEX
    Explanations

    instructions after download

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

    professions or people

    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
     פּ
    0.42
    疾患
    0.39
     במהלך
    0.38
     לפני
    0.38
     després
    0.37
    }=-\
    0.37
     uchun
    0.36
     utterly
    0.36
    ֶ
    0.36
    珮
    0.36
    POSITIVE LOGITS
     supermarkets
    0.42
     unscrupulous
    0.41
     suburban
    0.38
     fisherman
    0.38
     legally
    0.37
     burglar
    0.37
     Ulster
    0.37
     refinancing
    0.37
     fishermen
    0.36
     installed
    0.35
    Activations Density 0.000%

    No Known Activations