© 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. 77554
    Prev
    Next
    INDEX
    Explanations

    ranked a, die by, stainless steel, customize for

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

    programming, design, processing, performance

    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
    ،
    0.50
     quelconque
    0.48
    ፣
    0.48
     आपण
    0.46
    i
    0.46
    、
    0.44
     Certaines
    0.43
     மற்ற
    0.43
     मिला
    0.43
     आपल्याला
    0.42
    POSITIVE LOGITS
     CEF
    0.44
    ulfide
    0.42
    asr
    0.41
    лли
    0.40
    َاب
    0.40
    кур
    0.40
    𝙉
    0.40
    selfish
    0.39
    accam
    0.38
     গোলাবার
    0.38
    Activations Density 0.001%

    No Known Activations