© 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. 39463
    Prev
    Next
    INDEX
    Explanations

    contact information, sales, or foreign text

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

    foreign or mixed-language descriptions

    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
     deutschen
    0.43
     Models
    0.41
     multil
    0.41
     berger
    0.41
    ž
    0.41
     multiverse
    0.40
    刹
    0.40
     ber
    0.40
     dynamics
    0.40
     multinational
    0.40
    POSITIVE LOGITS
     nuovamente
    0.49
     проще
    0.47
     শুনানি
    0.46
    )=(\
    0.46
    ApiPath
    0.45
    ؟!
    0.45
     wynika
    0.45
    会将
    0.45
     আবারও
    0.45
     придется
    0.44
    Activations Density 0.000%

    No Known Activations