© 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. 26789
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

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

    Rentry page or investments

    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
    ]=-
    0.52
     desag
    0.52
     conglomerates
    0.51
    ће
    0.50
     dermatitis
    0.48
     compleja
    0.48
     institutes
    0.47
     института
    0.47
    ໕
    0.47
    UnderWater
    0.46
    POSITIVE LOGITS
    island
    0.47
     S
    0.44
     AUDIO
    0.43
    gado
    0.42
    rt
    0.42
     Jos
    0.41
    id
    0.41
     পরেও
    0.41
     erbjud
    0.41
     தன்மை
    0.41
    Activations Density 0.000%

    No Known Activations