© 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. 202271
    Prev
    Next
    INDEX
    Explanations

    securely followed by you; tag gallery

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

    instructions, answers, comfortable partner

    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
    🛶
    0.51
     airtight
    0.49
     απαι
    0.47
     futuristic
    0.47
    EY
    0.47
     acre
    0.46
     TeV
    0.45
     unlimited
    0.45
    アクセ
    0.45
     solubility
    0.44
    POSITIVE LOGITS
    م
    0.55
    ت
    0.54
    tnie
    0.50
     ست
    0.50
    tw
    0.49
    ट्टे
    0.49
    omètre
    0.47
    alo
    0.47
    icción
    0.47
     बृ
    0.47
    Activations Density 0.000%

    No Known Activations