© 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. 169741
    Prev
    Next
    INDEX
    Explanations

    Go over your rental agreement

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

    when

    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
    n
    0.58
    re
    0.57
    consumption
    0.56
    و
    0.55
    por
    0.52
    al
    0.49
    probably
    0.48
    bbs
    0.48
    nbs
    0.48
    o
    0.48
    POSITIVE LOGITS
     lashes
    0.48
     mettent
    0.48
    iczna
    0.45
     proposent
    0.45
     eignet
    0.44
     catheters
    0.44
    ışt
    0.44
     appartient
    0.44
     modulates
    0.44
    的长
    0.43
    Activations Density 0.001%

    No Known Activations