© 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. 122000
    Prev
    Next
    INDEX
    Explanations

    general information

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

    but still

    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
     ফটোগ্রাফ
    0.53
    賬
    0.49
    Blending
    0.48
     ਦ
    0.46
    сног
    0.44
    ཱ
    0.44
    AllRef
    0.43
     раху
    0.43
    花了
    0.43
    火焰
    0.43
    POSITIVE LOGITS
     Gerais
    0.50
     (-)
    0.50
     generales
    0.48
     gerais
    0.47
     myths
    0.46
     Myths
    0.46
     General
    0.46
     Genel
    0.45
     general
    0.45
     Popul
    0.45
    Activations Density 0.002%

    No Known Activations