© 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. 91882
    Prev
    Next
    INDEX
    Explanations

    systems and processes

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

    books, haven, Chinatown, acknowledges, thread, distributes

    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
    শ্ত
    0.50
     probs
    0.49
     overwhelm
    0.48
     Atelier
    0.46
     overwhelmingly
    0.46
     expend
    0.46
    い
    0.46
    にあ
    0.45
    renched
    0.45
     ,
    0.45
    POSITIVE LOGITS
    ээ
    0.54
    Reco
    0.52
    häng
    0.51
    uración
    0.51
    Bitmap
    0.50
    獲得
    0.48
    ن
    0.47
    ρώ
    0.47
    Metering
    0.47
    لي
    0.47
    Activations Density 0.000%

    No Known Activations