© 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. 181223
    Prev
    Next
    INDEX
    Explanations

    ebooks and annual publications

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

    acknowledging and explaining opinions

    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
    EtOH
    0.51
    如下图
    0.51
    certs
    0.45
     golpes
    0.43
    격
    0.43
     saddhim
    0.43
    上午
    0.43
     советы
    0.41
    碉
    0.41
     respectivas
    0.41
    POSITIVE LOGITS
     anual
    0.48
     to
    0.45
     untersucht
    0.45
     doing
    0.44
     yıllık
    0.44
     on
    0.44
     annuel
    0.44
     Freunden
    0.43
     annually
    0.43
    čia
    0.43
    Activations Density 0.000%

    No Known Activations