© 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. 191881
    Prev
    Next
    INDEX
    Explanations

    list of routes

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

    artistic descriptions

    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
    <unused61>
    0.45
    その
    0.44
    NSInteger
    0.44
     "
    0.43
     hil
    0.43
     configurational
    0.43
     Fulton
    0.42
    -
    0.42
    .
    0.41
     to
    0.41
    POSITIVE LOGITS
     లె
    0.55
     कैंडिडेट्स
    0.51
    वायरमेंट
    0.49
    धात
    0.48
    璨
    0.48
    𝚍
    0.48
     PDT
    0.47
     પેટ
    0.47
    ≺
    0.47
    щё
    0.47
    Activations Density 0.001%

    No Known Activations