© 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. 143754
    Prev
    Next
    INDEX
    Explanations

    things you need

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

    the glimpse beyond

    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
    蟲
    0.50
    クーポン
    0.48
    ಬಹುದ
    0.46
     因為
    0.46
    ncoder
    0.46
     nws
    0.46
    BackendAuth
    0.45
    釘
    0.45
    볐
    0.44
    нити
    0.44
    POSITIVE LOGITS
    ice
    0.52
     I
    0.51
    artige
    0.45
     vin
    0.43
    K
    0.42
    ات
    0.42
    呼
    0.41
    inv
    0.41
     i
    0.41
    El
    0.41
    Activations Density 0.001%

    No Known Activations