© 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. 179512
    Prev
    Next
    INDEX
    Explanations

    academic or factual descriptions

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

    disclaimers, warnings, concerns, instructions

    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
     বল
    0.57
    អំ
    0.52
    ilah
    0.51
     市
    0.50
    โบ
    0.49
     समृद्ध
    0.48
    aneous
    0.47
     अनेक
    0.47
     मनात
    0.47
     เมือง
    0.46
    POSITIVE LOGITS
    무리
    0.46
     aprende
    0.46
     realizará
    0.45
     aprendiz
    0.44
     listener
    0.44
    :”
    0.44
     ACD
    0.43
    ඤ
    0.43
     asist
    0.43
     modifica
    0.42
    Activations Density 0.000%

    No Known Activations