© 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. 97746
    Prev
    Next
    INDEX
    Explanations

    limited run

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

    fixed number or count

    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
     संघर्ष
    0.47
    现在
    0.47
    难道
    0.46
    击
    0.46
    我说
    0.45
    我现在
    0.44
    㴡
    0.44
    鐧
    0.43
    ęd
    0.43
    ່ງ
    0.43
    POSITIVE LOGITS
    買う
    0.55
     makeover
    0.50
     probabilistic
    0.48
     menentukan
    0.45
     solving
    0.45
     predictable
    0.45
     rerun
    0.45
     predictive
    0.45
     September
    0.44
     prediction
    0.44
    Activations Density 0.002%

    No Known Activations