© 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. 249364
    Prev
    Next
    INDEX
    Explanations

    reasonable period, different firmness

    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
    ift
    0.45
    써
    0.41
     reviewers
    0.40
     거예요
    0.40
     пот
    0.40
    ilos
    0.40
    軟
    0.40
     combustibles
    0.39
     Eddie
    0.39
     संस्कार
    0.39
    POSITIVE LOGITS
    㓶
    0.50
     영역
    0.50
     Aşağı
    0.49
     Dön
    0.49
     পশ্চিমা
    0.49
     regione
    0.48
     ദി
    0.48
    Fernseh
    0.48
    沨
    0.48
     നമ്പർ
    0.47
    Activations Density 0.001%

    No Known Activations