© 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. 89316
    Prev
    Next
    INDEX
    Explanations

    enumeration or listings

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

    questions about needs or traits

    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
    리면
    0.53
     $\#
    0.42
     hubiera
    0.41
    gles
    0.40
     miesto
    0.40
     harp
    0.39
     eluted
    0.39
     минуту
    0.38
     preferably
    0.38
    \\\
    0.38
    POSITIVE LOGITS
     inmobili
    0.46
     bölüm
    0.45
    मा
    0.45
    €
    0.45
     অবিশ্বাস
    0.44
     कारा
    0.44
     Proces
    0.43
     proces
    0.43
    proces
    0.42
     Dasar
    0.42
    Activations Density 0.000%

    No Known Activations