© 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. 186306
    Prev
    Next
    INDEX
    Explanations

    numbers and specific words like 'school'

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

    sites, exam, eggs, exchange

    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
    projekt
    0.51
    <unused32>
    0.50
    Projekt
    0.49
    AZIONE
    0.48
    <unused77>
    0.48
     benötigen
    0.48
     semelhante
    0.48
     životu
    0.47
    ഓ
    0.47
     berbah
    0.46
    POSITIVE LOGITS
    极
    0.49
     extremes
    0.45
     discrepancy
    0.41
    萎
    0.41
     thickness
    0.40
     ROT
    0.40
     трак
    0.40
    秘
    0.40
    常
    0.40
    惊
    0.40
    Activations Density 0.000%

    No Known Activations