© 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. 37199
    Prev
    Next
    INDEX
    Explanations

    a land

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

    time within expected parameters

    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
    에
    0.55
    ът
    0.51
     hollywood
    0.50
    짤
    0.50
    ές
    0.49
     sprinkled
    0.47
    ໊
    0.46
     ingrédients
    0.46
     cigars
    0.46
     dólares
    0.45
    POSITIVE LOGITS
     efficacy
    0.54
     VOC
    0.47
    <unused2128>
    0.46
     by
    0.42
     Tü
    0.42
     এইরূপে
    0.42
     Swedish
    0.41
     JN
    0.41
     Ng
    0.40
    ByUser
    0.40
    Activations Density 0.000%

    No Known Activations