© 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. 152456
    Prev
    Next
    INDEX
    Explanations

    website, site, yourself, different, papers, HM

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

    website, Database Design, nitrogen fixation

    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
     stared
    0.52
     resumed
    0.51
     سلامه
    0.50
    ቾ
    0.49
     solicitudes
    0.48
     detectable
    0.48
    echolog
    0.47
     sheared
    0.46
     کولی
    0.46
     sejam
    0.46
    POSITIVE LOGITS
    ু
    0.52
    ก
    0.50
    ্ম
    0.50
    ्ट
    0.46
    Maps
    0.44
    Luckily
    0.44
    Payout
    0.44
     koment
    0.44
    ্ত
    0.43
    ্মা
    0.43
    Activations Density 0.000%

    No Known Activations