© 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. 22048
    Prev
    Next
    INDEX
    Explanations

    network ping statistics

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

    Unit designation

    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
     рік
    0.54
     triplets
    0.49
     age
    0.45
     ages
    0.44
    얘
    0.44
     AGE
    0.43
     Kenny
    0.43
    ležit
    0.42
     やつ
    0.42
    0.42
    POSITIVE LOGITS
    ti
    0.52
    ski
    0.51
    т
    0.48
    ای
    0.46
    ুয়া
    0.46
    Abs
    0.46
    PTV
    0.45
    sq
    0.44
    abad
    0.44
    τικ
    0.44
    Activations Density 0.000%

    No Known Activations