© 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. 229340
    Prev
    Next
    INDEX
    Explanations

    preventive maintenance on

    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
    渠道
    0.53
    ᄒ
    0.52
     attham
    0.50
    ومت
    0.48
    荃
    0.47
     ወይም
    0.46
     observé
    0.46
    右手
    0.46
    لل
    0.46
    旪
    0.45
    POSITIVE LOGITS
     pink
    0.61
     silicon
    0.59
     lockdown
    0.55
     per
    0.53
     sa
    0.53
     z
    0.52
     bank
    0.51
     troll
    0.50
     tomb
    0.50
     terrific
    0.49
    Activations Density 0.001%

    No Known Activations