© 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. 33690
    Prev
    Next
    INDEX
    Explanations

    platform

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

    declarations, environment, count, switches, ordering

    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
    斯
    0.42
     ಸ್ವಲ್ಪ
    0.38
     में
    0.38
    による
    0.38
     be
    0.38
     זה
    0.36
    ľa
    0.36
     บาง
    0.36
     пере
    0.35
     を
    0.35
    POSITIVE LOGITS
     Phenomena
    0.35
    শ্রে
    0.32
    現象
    0.31
     दावे
    0.31
     phenomenon
    0.31
    কিন্তু
    0.30
     championed
    0.30
    랫폼
    0.30
     ylabel
    0.30
    তিরিক্ত
    0.30
    Activations Density 0.009%

    No Known Activations