© 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. 14199
    Prev
    Next
    INDEX
    Explanations

    way to pictures

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

    first or second

    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
     résultats
    0.46
     McQu
    0.43
     नि
    0.41
     প্রসঙ্গ
    0.41
    <unused70>
    0.41
     વધુ
    0.40
     निष्कर्ष
    0.40
    풉
    0.40
     صحت
    0.40
     অনলাইনে
    0.40
    POSITIVE LOGITS
     kettle
    0.44
     Think
    0.44
     coaction
    0.43
     example
    0.41
    exemple
    0.40
     first
    0.40
     cocoa
    0.40
    ibil
    0.39
     stand
    0.39
     due
    0.38
    Activations Density 0.000%

    No Known Activations