© 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. 36698
    Prev
    Next
    INDEX
    Explanations

    complex choices

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

    technical specifications and outcomes

    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
    贰百
    0.50
    जनबी
    0.47
     halloween
    0.47
    édie
    0.45
    Halloween
    0.44
    اسى
    0.44
    duire
    0.43
    鐏
    0.42
    ėje
    0.41
     publice
    0.41
    POSITIVE LOGITS
    shim
    0.49
    🫶
    0.45
    ymen
    0.42
    typical
    0.42
     বেশিরভাগ
    0.42
     zaključ
    0.41
     προβ
    0.41
     obviously
    0.41
     fortement
    0.41
     متوسط
    0.40
    Activations Density 0.000%

    No Known Activations