© 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. 164164
    Prev
    Next
    INDEX
    Explanations

    like twins

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

    "use", "quantification", "monastery", "outright", "once", "estimated", "while"

    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
     ActionResult
    0.41
     Cyst
    0.41
    討論
    0.41
     fussy
    0.40
    ParameterActive
    0.38
    *\*
    0.38
     reff
    0.38
    يمي
    0.38
    يسي
    0.37
     adjudicated
    0.37
    POSITIVE LOGITS
     יותר
    0.50
    veille
    0.48
    phosph
    0.47
    द्वार
    0.47
    ประตู
    0.47
     mundo
    0.47
    порт
    0.47
     atual
    0.46
     gerais
    0.46
    ש
    0.46
    Activations Density 0.000%

    No Known Activations