© 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. 106548
    Prev
    Next
    INDEX
    Explanations

    technical, professional, and specific contexts

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

    inspired byfundamental relationshipself assurednessproductsmonetary values

    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
     HID
    0.44
    autoload
    0.44
    수록
    0.43
     തുടങ്ങിയ
    0.42
    }.
    0.42
     respectable
    0.41
     nigra
    0.41
     river
    0.41
     sloping
    0.40
    POSITIVE LOGITS
     प्रोडक्शन
    0.50
    ooo
    0.49
    marvel
    0.49
    𝘸
    0.48
    ві
    0.48
    STER
    0.48
    oh
    0.47
    מה
    0.47
    𝗣
    0.47
    ཋ
    0.47
    Activations Density 0.000%

    No Known Activations