© 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. 86090
    Prev
    Next
    INDEX
    Explanations

    ClientHttpRequestInterceptor

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

    programming constructs like Init, Executor, Receiver

    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
    type
    0.48
        
    0.46
    <h2>
    0.45
     jako
    0.44
              
    0.44
     TreeNode
    0.44
    <h3>
    0.43
    ")
    0.42
    )=
    0.41
    PHONE
    0.41
    POSITIVE LOGITS
    藝術
    0.52
     mân
    0.47
    ຢູ່
    0.47
     ఇది
    0.46
    艺术
    0.44
    城的
    0.44
    <unused78>
    0.44
    assignmentItems
    0.43
    UILLER
    0.43
     моих
    0.43
    Activations Density 0.000%

    No Known Activations