© 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. 133958
    Prev
    Next
    INDEX
    Explanations

    types of services

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

    past performance or future results

    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
     ऐड
    0.48
     appreciates
    0.45
     참
    0.44
     ToString
    0.44
     एरो
    0.43
     Spielen
    0.43
    érrez
    0.42
     understands
    0.42
    များ
    0.42
     appreciate
    0.42
    POSITIVE LOGITS
    ajib
    0.47
     suro
    0.47
    ły
    0.46
     tanpa
    0.45
     sangat
    0.44
     calf
    0.44
    (
    0.44
     peng
    0.43
    ισ
    0.43
     regulator
    0.43
    Activations Density 0.000%

    No Known Activations