© 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. 148444
    Prev
    Next
    INDEX
    Explanations

    legal and business clauses

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

    finding possible decompositions

    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
    ना
    0.51
    ٹ
    0.46
    멘
    0.44
    ذ
    0.43
    טר
    0.43
    ით
    0.42
    ्ल
    0.42
    功能
    0.41
    ת
    0.41
    동
    0.41
    POSITIVE LOGITS
     multitask
    0.55
     bedrijven
    0.54
     vrouw
    0.50
     hypothesize
    0.50
     compagnies
    0.48
     volgens
    0.48
     gravité
    0.47
     locatie
    0.47
    ന്ഥ
    0.47
     ডিজ
    0.47
    Activations Density 0.001%

    No Known Activations