© 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. 163494
    Prev
    Next
    INDEX
    Explanations

    options connected by or

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

    not just or not entirely

    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
     february
    0.52
     TERM
    0.47
     deform
    0.46
     よく
    0.45
     மரியாதை
    0.45
    }):
    0.45
     decoder
    0.44
     yawn
    0.43
    ではない
    0.43
    incomplete
    0.42
    POSITIVE LOGITS
     LoginPage
    0.54
     里
    0.48
     ऐप्स
    0.46
    btnLogin
    0.44
     اتح
    0.44
    LoginPage
    0.44
     Riche
    0.43
     জাতীয়
    0.43
     thất
    0.43
    ählten
    0.43
    Activations Density 0.000%

    No Known Activations