© 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-16K
    7. 12414
    Prev
    Next
    INDEX
    Explanations

    rated X out of X

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

    rating 5 stars

    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_16k_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
     együtt
    0.47
    范围
    0.45
    噺
    0.42
     rough
    0.42
    []');
    0.42
    Menu
    0.41
     разобра
    0.40
     sebaik
    0.40
    rough
    0.40
     जाएंगे
    0.40
    POSITIVE LOGITS
     Chance
    0.39
     LH
    0.38
     সামগ্র
    0.38
     पिछली
    0.38
    stest
    0.38
    ❣
    0.38
    বারের
    0.38
     Admittedly
    0.37
     факт
    0.37
    ück
    0.36
    Activations Density 0.046%

    No Known Activations