© 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. 66050
    Prev
    Next
    INDEX
    Explanations

    scale back calories

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

    payment details

    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
    p
    0.56
    bridge
    0.54
    rend
    0.50
    fa
    0.49
    cube
    0.49
    adap
    0.48
    o
    0.48
    ass
    0.47
    pend
    0.47
    pulse
    0.47
    POSITIVE LOGITS
     bolstering
    0.50
     voluntarily
    0.50
     Autumn
    0.49
     ridiculed
    0.49
     जूस
    0.48
     ከዚያ
    0.48
    箩
    0.48
     praised
    0.47
     Lotion
    0.46
    헛
    0.46
    Activations Density 0.000%

    No Known Activations