© 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. 109908
    Prev
    Next
    INDEX
    Explanations

    development of items

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

    facebook marketplace posts

    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
    位的
    0.48
    wijl
    0.47
     অবস্থায়
    0.46
    ებმა
    0.46
     środ
    0.46
    ъ
    0.46
    ăl
    0.44
     বাহ
    0.44
    ("")
    0.43
    ți
    0.43
    POSITIVE LOGITS
     epidemics
    0.52
     flair
    0.52
     glaciers
    0.52
     flares
    0.51
     idols
    0.51
     spines
    0.50
     llamas
    0.49
     prawns
    0.48
     gills
    0.46
     a
    0.46
    Activations Density 0.001%

    No Known Activations