© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 213117
    Prev
    Next
    INDEX
    Explanations

    cybersecurity and system partitions

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

    2 GB RAM recommendations

    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
     Some
    0.43
    lj
    0.42
    ل
    0.42
     Three
    0.40
     प्रि
    0.40
    underline
    0.40
     Rous
    0.39
     چنانچہ
    0.39
     chloro
    0.39
     بج
    0.38
    POSITIVE LOGITS
     складу
    0.53
     personalizada
    0.52
     raven
    0.52
    ὅ
    0.50
     postérieur
    0.48
     договору
    0.48
     mètre
    0.48
    чної
    0.47
    ચ્
    0.47
     processi
    0.47
    Activations Density 0.000%

    No Known Activations