© 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. 248419
    Prev
    Next
    INDEX
    Explanations

    process or example

    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
     ["
    0.45
    etano
    0.44
    ierend
    0.44
    たっぷ
    0.43
     trova
    0.42
     pines
    0.41
     retr
    0.41
     dej
    0.41
    特集
    0.41
     उत्साह
    0.41
    POSITIVE LOGITS
     authorise
    0.42
     interrogate
    0.42
     requestCode
    0.41
    筋
    0.41
     жүкт
    0.40
     intercom
    0.40
     automate
    0.39
     automation
    0.39
     divorce
    0.39
    复杂度
    0.39
    Activations Density 0.001%

    No Known Activations