© 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. 15624
    Prev
    Next
    INDEX
    Explanations

    NGOs and commercial ventures

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

    business and marketing

    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
    stuhl
    0.43
    ྪ
    0.43
    ní
    0.42
     erforderlich
    0.40
    𝓵
    0.40
    及び
    0.40
    および
    0.39
    ın
    0.38
    胧
    0.38
    stil
    0.38
    POSITIVE LOGITS
     supermarkets
    0.59
     entrepreneurs
    0.57
     market
    0.56
     marketers
    0.54
     groceries
    0.52
     NGOs
    0.52
     philanthropy
    0.50
     weddings
    0.50
     markets
    0.49
     influencers
    0.48
    Activations Density 0.000%

    No Known Activations