© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72589
    Prev
    Next
    INDEX
    Explanations

    renting dumpsters

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

    breakdown of why

    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
    állítás
    0.49
    টিত
    0.48
    거나
    0.46
    andır
    0.46
     அல்லது
    0.45
    ceu
    0.43
    ঞ
    0.42
    ্যাস
    0.42
    или
    0.42
    كز
    0.42
    POSITIVE LOGITS
     donner
    0.49
     chock
    0.45
    gifts
    0.45
     sentimento
    0.44
     قيمة
    0.43
    ۖ
    0.42
     diferencias
    0.42
     Chaud
    0.41
     tranche
    0.41
     gifts
    0.41
    Activations Density 0.001%

    No Known Activations