© 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. 52709
    Prev
    Next
    INDEX
    Explanations

    during or after breaks

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

    commuting situations and experiences

    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
    issue
    0.47
    ث
    0.44
    θε
    0.43
    Jf
    0.42
    '
    0.42
     issue
    0.42
    jo
    0.42
    انی
    0.42
    ifu
    0.42
    POSITIVE LOGITS
     während
    0.47
     বিশ্র
    0.44
     During
    0.44
    额外的
    0.44
     nghỉ
    0.43
     detour
    0.43
     multitasking
    0.43
    もある
    0.42
    Electro
    0.42
     还
    0.42
    Activations Density 0.000%

    No Known Activations