© 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. 150713
    Prev
    Next
    INDEX
    Explanations

    specific names and entities

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

    contextualized explanations

    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
     સર્
    0.57
     регули
    0.55
     دو
    0.53
    джа
    0.51
    CapsLock
    0.51
     श्रृ
    0.50
    ádza
    0.50
    蚪
    0.50
     વી
    0.50
    ení
    0.49
    POSITIVE LOGITS
    UN
    0.51
     experts
    0.47
     fumes
    0.47
     rank
    0.45
     juveniles
    0.45
     configurations
    0.44
     K
    0.43
    Os
    0.43
     triangles
    0.43
     clashes
    0.43
    Activations Density 0.000%

    No Known Activations