© 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. 240106
    Prev
    Next
    INDEX
    Explanations

    . , '

    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
    量
    0.47
     \"
    0.43
    量的
    0.43
    有多
    0.42
    文化的
    0.42
    用来
    0.42
    နိုင်
    0.41
    用户的
    0.41
    \",
    0.41
     perceive
    0.41
    POSITIVE LOGITS
    پ
    0.47
    گ
    0.47
     annuel
    0.46
     ativo
    0.46
     attivo
    0.46
    topology
    0.46
     famille
    0.45
    LON
    0.45
    𝗿
    0.44
    produto
    0.44
    Activations Density 0.002%

    No Known Activations