© 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. 105173
    Prev
    Next
    INDEX
    Explanations

    stretch the defense

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

    bridge population Gandalf Liter Batch According

    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
    າຍ
    0.46
     פרו
    0.45
    PRINC
    0.44
    OTROS
    0.44
    량
    0.44
    ANTE
    0.44
    JACK
    0.44
    수
    0.44
    ﮑ
    0.43
    은
    0.42
    POSITIVE LOGITS
     smtp
    0.54
     medie
    0.52
     Magento
    0.50
     Vodafone
    0.49
     Apache
    0.47
     Ajax
    0.47
     Reza
    0.46
     Oktoberfest
    0.46
    érard
    0.46
     Alex
    0.45
    Activations Density 0.004%

    No Known Activations