© 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. 116030
    Prev
    Next
    INDEX
    Explanations

    phrase or word

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

    equations and measurements

    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
    ारा
    0.62
    uestos
    0.52
    ன
    0.51
    ன்
    0.49
     улица
    0.48
     schneller
    0.48
     н
    0.48
    न
    0.47
     tarses
    0.47
    ான்
    0.47
    POSITIVE LOGITS
    Glam
    0.52
     vou
    0.48
     discern
    0.47
     privileged
    0.45
     Glam
    0.44
     Fiat
    0.44
     began
    0.43
     fascin
    0.43
    సర్
    0.43
     Wine
    0.43
    Activations Density 0.000%

    No Known Activations