© 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. 111471
    Prev
    Next
    INDEX
    Explanations

    eProcurement, case, friend, sand, should, brand, for, been, immersed

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

    involve in language and structure

    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
     ön
    0.46
     on
    0.45
     Lach
    0.43
     Des
    0.43
    },"
    0.43
     des
    0.42
     при
    0.41
     Lato
    0.41
    imageUrl
    0.41
     Lakeland
    0.41
    POSITIVE LOGITS
    หมือน
    0.45
    IOT
    0.45
    बड़े
    0.44
    IO
    0.44
     договора
    0.43
    fficacy
    0.43
     پورے
    0.42
    হ্যা
    0.42
    Ũ
    0.41
    бір
    0.41
    Activations Density 0.000%

    No Known Activations