© 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. 165623
    Prev
    Next
    INDEX
    Explanations

    introducing examples or specifics

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

    often used for background

    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
     تار
    0.55
     காண
    0.47
     डिट
    0.46
    萜
    0.46
    Nau
    0.44
    OH
    0.44
     கண்டு
    0.43
     нау
    0.43
     بینی
    0.43
     नष्ट
    0.42
    POSITIVE LOGITS
     invincible
    0.48
     unbeatable
    0.45
    ᅨ
    0.44
    い
    0.42
    ,\
    0.42
     المدرسة
    0.41
     underpinned
    0.41
     beispielsweise
    0.40
     agreed
    0.40
     частности
    0.40
    Activations Density 0.001%

    No Known Activations