© 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. 99279
    Prev
    Next
    INDEX
    Explanations

    consortium

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

    what are factors and limitations

    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
     územ
    0.50
    蕌
    0.46
     antif
    0.46
     mies
    0.44
    Ⴌ
    0.44
     geospatial
    0.44
    အစိတ်အပိုင်း
    0.44
     tredje
    0.44
    പോലെ
    0.44
     CMake
    0.43
    POSITIVE LOGITS
    rom
    0.44
    icus
    0.42
    dent
    0.42
    "
    0.41
    ron
    0.41
    pounds
    0.41
    n
    0.40
    rians
    0.40
    rou
    0.40
    man
    0.39
    Activations Density 0.000%

    No Known Activations