© 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. 35875
    Prev
    Next
    INDEX
    Explanations

    grand jury, big announcement, load balancer

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

    loss of control

    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
    蒿
    0.44
    কেন্দ্র
    0.43
     Boer
    0.43
     SLAs
    0.43
    тья
    0.42
    هلا
    0.42
    ष्कार
    0.42
     yd
    0.42
    pale
    0.41
     கிரக
    0.41
    POSITIVE LOGITS
     assay
    0.45
    ovod
    0.44
    ");
    0.43
     листопада
    0.42
     तपास
    0.42
    Makefile
    0.41
     |_{
    0.41
     >;
    0.40
     '>'
    0.39
     входят
    0.39
    Activations Density 0.000%

    No Known Activations