© 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. 34671
    Prev
    Next
    INDEX
    Explanations

    millennial-favourite, Danish brand Ganni

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

    various concepts and terminology

    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
    ​
    0.45
    <0x81>
    0.40
    varo
    0.39
    trx
    0.38
    <0xA0>
    0.38
     richly
    0.37
    로부터
    0.37
     накопи
    0.37
    phic
    0.37
    spě
    0.37
    POSITIVE LOGITS
     errado
    0.49
     elegido
    0.47
     declaraciones
    0.47
    氦
    0.47
     பயிற்
    0.46
     incorrectly
    0.46
     जाति
    0.44
     secciones
    0.44
     Alemania
    0.43
     falso
    0.43
    Activations Density 0.000%

    No Known Activations