© 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. 252077
    Prev
    Next
    INDEX
    Explanations

    stamp cover

    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
     businesses
    0.45
    一些
    0.43
    ند
    0.42
    sched
    0.42
    艱
    0.42
    大変
    0.42
     tabella
    0.41
     snacking
    0.41
    adt
    0.40
    χο
    0.40
    POSITIVE LOGITS
     JOSEPH
    0.50
    ONOM
    0.48
     figli
    0.47
    ान
    0.47
     autrefois
    0.46
     美国
    0.46
    CLES
    0.46
     xhrObj
    0.46
    ∶
    0.46
     连接
    0.46
    Activations Density 0.000%

    No Known Activations