© 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. 137685
    Prev
    Next
    INDEX
    Explanations

    foods and beverages

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

    negative consequences

    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
    ліза
    0.47
     हंस
    0.46
    揉
    0.46
     самая
    0.45
     приня
    0.45
    妧
    0.44
    ย
    0.44
    ਟ
    0.44
    िरपेक्ष
    0.43
    तुम्हारा
    0.43
    POSITIVE LOGITS
     beverages
    0.59
     appetizers
    0.56
     Foods
    0.55
     droughts
    0.54
     foods
    0.54
    ;
    0.54
     at
    0.53
     Food
    0.52
     breakfasts
    0.52
     vaccines
    0.51
    Activations Density 0.000%

    No Known Activations