© 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. 45039
    Prev
    Next
    INDEX
    Explanations

    .com websites

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

    collected data, internet, manufacturing, wants

    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
     Speaker
    0.50
     शंकर
    0.46
     Overwatch
    0.45
    Speaker
    0.45
     Addiction
    0.43
     Classic
    0.43
     (
    0.42
     ανο
    0.42
     শাখা
    0.41
     Defense
    0.40
    POSITIVE LOGITS
    ]">
    0.50
     rezult
    0.49
     obsah
    0.49
     э
    0.49
    ез
    0.48
     mannit
    0.47
    prés
    0.47
     offrent
    0.47
     hydraz
    0.47
    เอ
    0.46
    Activations Density 0.000%

    No Known Activations