© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202025
    Prev
    Next
    INDEX
    Explanations

    interest and attendance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     चढ़ा
    0.51
    <unused348>
    0.47
     EFFECT
    0.45
     πραγμα
    0.45
     સમ
    0.44
    <unused683>
    0.44
    <unused698>
    0.44
    <unused1062>
    0.44
    ỷ
    0.44
    䂘
    0.44
    POSITIVE LOGITS
     molde
    0.47
     ejac
    0.47
     stripper
    0.45
     hemi
    0.45
     invite
    0.44
     attend
    0.43
    ped
    0.42
     attends
    0.42
    Attend
    0.42
    اد
    0.42
    Activations Density 0.001%

    No Known Activations