© 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. 202887
    Prev
    Next
    INDEX
    Explanations

    nominee shareholder, director, ambassador, railway

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

    considering, used, formal

    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
     evade
    0.54
    प्लेक्स
    0.49
    дав
    0.48
     செல்வ
    0.47
     ovviamente
    0.47
     extinguish
    0.46
     absorb
    0.46
    :>
    0.46
     dissipate
    0.46
     ()=>
    0.46
    POSITIVE LOGITS
    Ye
    0.52
    Streaming
    0.44
    Que
    0.44
    Quest
    0.43
    ছবি
    0.42
    Conference
    0.41
     Daylight
    0.41
     चारों
    0.40
    streaming
    0.40
    Comm
    0.40
    Activations Density 0.001%

    No Known Activations