© 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. 161803
    Prev
    Next
    INDEX
    Explanations

    detailed analysis and descriptions

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

    details, Juniper, was

    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
    n
    0.51
    Discount
    0.46
    bout
    0.46
    Left
    0.45
    it
    0.45
    Off
    0.44
    water
    0.43
    its
    0.43
    Price
    0.43
    i
    0.43
    POSITIVE LOGITS
     nelle
    0.53
     verschiedene
    0.50
     seguenti
    0.50
     написано
    0.49
     në
    0.48
     nella
    0.47
     volgende
    0.46
     سمع
    0.46
     adatto
    0.45
     décrites
    0.45
    Activations Density 0.001%

    No Known Activations