© 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. 60792
    Prev
    Next
    INDEX
    Explanations

    tracking and monitoring

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

    octet rule

    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
    ुअल
    0.50
    ikiran
    0.45
    ουμε
    0.44
    䁂
    0.44
    拭
    0.44
    式の
    0.44
    駐
    0.43
    ípio
    0.43
    ات
    0.42
    獻
    0.42
    POSITIVE LOGITS
     Capri
    0.52
     Manufacturers
    0.50
     сатып
    0.48
     Seven
    0.47
     chans
    0.47
     July
    0.46
     przedsiębior
    0.46
     Why
    0.46
     Delta
    0.46
     zakup
    0.46
    Activations Density 0.000%

    No Known Activations