© 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. 236737
    Prev
    Next
    INDEX
    Explanations

    Report and Score

    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
    lav
    0.46
     cuisines
    0.46
    ।
    0.46
    Desde
    0.45
     درب
    0.44
     embank
    0.43
     चम्मच
    0.43
     -!
    0.42
    ]
    0.42
    quisites
    0.41
    POSITIVE LOGITS
    вае
    0.55
    argc
    0.49
     سك
    0.49
    report
    0.48
    ке
    0.47
     report
    0.46
     Skor
    0.46
    Report
    0.46
    ските
    0.45
    _{+}+
    0.44
    Activations Density 0.001%

    No Known Activations