© 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. 161029
    Prev
    Next
    INDEX
    Explanations

    Fontana opened depth thickness enough

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

    cards, brands, or readiness

    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
    ک
    0.45
    鐒
    0.45
     Shea
    0.44
    <start_of_image>
    0.43
    á
    0.43
    ᱤ
    0.43
    aku
    0.42
    밖
    0.42
     Kembali
    0.41
     Expedia
    0.41
    POSITIVE LOGITS
     المسي
    0.55
    resposta
    0.53
    基督教
    0.53
    തായി
    0.52
     publicado
    0.51
     pubblicato
    0.51
     квіт
    0.50
     mostrando
    0.50
     cristian
    0.50
     പ്രത്യേ
    0.50
    Activations Density 0.000%

    No Known Activations