© 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. 106145
    Prev
    Next
    INDEX
    Explanations

    communities report

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

    write my dating profile

    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
     grados
    0.46
     rey
    0.46
     day
    0.45
     przesz
    0.43
    戈
    0.43
     kral
    0.43
     iniciado
    0.43
    цию
    0.43
     يوم
    0.43
    ソ
    0.43
    POSITIVE LOGITS
     শ্
    0.50
     És
    0.48
     οδη
    0.47
    ုပ်တို့
    0.46
     이후
    0.46
    ע
    0.45
     signatories
    0.44
    ਰੀ
    0.44
     oppressive
    0.44
    өк
    0.43
    Activations Density 0.001%

    No Known Activations