© 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. 96469
    Prev
    Next
    INDEX
    Explanations

    call to discuss

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

    unique compared

    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
    agher
    0.48
    ண்முக
    0.47
    ਕ
    0.44
     disponer
    0.44
     transportasi
    0.41
    ichtigung
    0.41
    ிக
    0.41
    ग्रामीण
    0.40
     rumour
    0.40
    ıklı
    0.40
    POSITIVE LOGITS
     সপ্তাহে
    0.45
     إلى
    0.45
     جبت
    0.42
    ِب
    0.42
     esimerk
    0.42
     kneel
    0.42
     কিংবা
    0.42
    WEEK
    0.42
     INTO
    0.41
     случаях
    0.41
    Activations Density 0.001%

    No Known Activations