© 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. 132572
    Prev
    Next
    INDEX
    Explanations

    new year discussion speakers back

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

    sections, moments, agents, styles, ethics

    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
     یه
    0.53
    ='',
    0.53
     expandable
    0.49
     prawns
    0.47
    녁
    0.47
     walked
    0.46
     degassing
    0.46
     jorn
    0.46
     japon
    0.45
     petty
    0.45
    POSITIVE LOGITS
    áb
    0.51
     Belief
    0.49
    ísk
    0.48
     недоста
    0.47
    á
    0.45
    ../
    0.43
     Committee
    0.43
    פים
    0.42
     Theoretically
    0.42
    ਂ
    0.42
    Activations Density 0.000%

    No Known Activations