© 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. 183744
    Prev
    Next
    INDEX
    Explanations

    meuble tv pas cher

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

    urgent tasks

    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
    }:=
    0.48
    Ded
    0.47
     Duran
    0.46
     artikel
    0.45
    Dur
    0.45
    }=\
    0.45
    Tera
    0.44
    Kwa
    0.44
    }}
    0.44
    zet
    0.44
    POSITIVE LOGITS
    MSFontService
    0.45
     exquisitely
    0.45
     офис
    0.44
     progenitors
    0.44
    ❍
    0.43
     closets
    0.43
     العلاقات
    0.42
    ेंगे
    0.42
    Ꮞ
    0.41
    dresser
    0.41
    Activations Density 0.001%

    No Known Activations