© 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. 247184
    Prev
    Next
    INDEX
    Explanations

    achievements and excellence

    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
    તિ
    0.48
    ولو
    0.48
     recuerdo
    0.48
    लेट
    0.47
     tachy
    0.47
     utiliser
    0.46
    lanelet
    0.46
    ﺵ
    0.46
     mudah
    0.45
     shouldUse
    0.45
    POSITIVE LOGITS
     Corners
    0.50
    -
    0.50
     holding
    0.49
     Labs
    0.49
     tolerances
    0.47
     Engineer
    0.47
     corners
    0.46
     Trophy
    0.46
     Excellence
    0.46
     trophy
    0.44
    Activations Density 0.000%

    No Known Activations