© 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. 8356
    Prev
    Next
    INDEX
    Explanations

    numbers and ranges

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

    numbers and quantities

    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
    <unused19>
    0.33
     promul
    0.33
     راستہ
    0.31
    <unused2127>
    0.30
     lLoginID
    0.30
     downregulation
    0.30
    faulse
    0.29
     wszyst
    0.29
    人都
    0.29
     購入
    0.29
    POSITIVE LOGITS
    2
    0.44
    с
    0.44
    0.43
    5
    0.43
    3
    0.41
    1
    0.40
     С
    0.38
    6
    0.38
    7
    0.38
    ↵
    0.38
    Activations Density 0.121%

    No Known Activations