© 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. 33211
    Prev
    Next
    INDEX
    Explanations

    easy and descriptive phrases

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

    captivating narrative, fascinating journey

    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
     악
    0.46
     좋
    0.46
     കത്തി
    0.43
     evenly
    0.42
     좋은
    0.42
     rho
    0.42
     ({
    0.42
     제곱
    0.42
     높은
    0.41
     najbolje
    0.41
    POSITIVE LOGITS
    ssel
    0.44
    shows
    0.41
    pad
    0.38
     fil
    0.37
    ws
    0.37
    show
    0.37
    looking
    0.37
    sp
    0.37
    sets
    0.37
     zug
    0.37
    Activations Density 0.000%

    No Known Activations