© 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. 149568
    Prev
    Next
    INDEX
    Explanations

    asking about costs and investments

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

    specific words and following punctuation

    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
     BIG
    0.48
     ER
    0.48
     NEXT
    0.47
     ID
    0.46
    ValMap
    0.45
    ,
    0.45
     CLEAR
    0.44
     TikTok
    0.44
     Instagram
    0.44
     VPS
    0.44
    POSITIVE LOGITS
    sack
    0.53
    anal
    0.52
    ሰው
    0.52
    ocr
    0.52
    changed
    0.50
    flavored
    0.49
    ڑ
    0.49
    سٹم
    0.48
    simulation
    0.48
    étendue
    0.48
    Activations Density 0.000%

    No Known Activations