© 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. 202894
    Prev
    Next
    INDEX
    Explanations

    list, class, interface

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

    hypnagogic pop and research terms

    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
    息
    0.46
    偶然
    0.44
    bian
    0.42
     虽然
    0.41
    वती
    0.41
    GUN
    0.40
    ployment
    0.40
    ানু
    0.39
    烬
    0.39
    Baker
    0.38
    POSITIVE LOGITS
     depre
    0.53
     עו
    0.48
     empat
    0.46
     dismin
    0.46
     erfol
    0.45
    듬
    0.45
     representa
    0.45
     gingen
    0.45
    ворю
    0.44
     станда
    0.44
    Activations Density 0.001%

    No Known Activations