© 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. 5342
    Prev
    Next
    INDEX
    Explanations

    handyman, HAYS, sandwich, properties

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

    originating from

    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
    尼亚
    0.52
     예술
    0.47
    姩
    0.47
    ญิง
    0.46
    нула
    0.46
    蘼
    0.46
     पर्यटक
    0.46
     музея
    0.45
    Tourist
    0.45
    चाकी
    0.45
    POSITIVE LOGITS
     H
    0.53
     “
    0.52
    0.52
     Con
    0.50
     O
    0.48
     Cl
    0.47
    hor
    0.47
     Das
    0.47
    6
    0.47
    ac
    0.46
    Activations Density 0.019%

    No Known Activations