© 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. 58436
    Prev
    Next
    INDEX
    Explanations

    purposes

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

    common following purposes

    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
    től
    0.49
     τ
    0.46
    θο
    0.44
     කර
    0.43
     ϒ
    0.43
     ór
    0.42
     resTmp
    0.42
     therefor
    0.41
     ましょう
    0.41
     သ
    0.41
    POSITIVE LOGITS
     purposes
    1.50
     sake
    1.47
     Purposes
    1.05
     Sake
    0.88
    来说
    0.62
     целей
    0.61
    來說
    0.61
     betterment
    0.60
     reasons
    0.57
    goes
    0.53
    Activations Density 0.527%

    No Known Activations