© 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. 22387
    Prev
    Next
    INDEX
    Explanations

    places and events

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

    why RODC?

    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
    γη
    0.49
    𝗹
    0.49
    łos
    0.47
    зі
    0.47
    𝗶
    0.45
     автоматтары
    0.45
     lời
    0.44
    ipa
    0.44
    χη
    0.44
     જોડ
    0.43
    POSITIVE LOGITS
     Elvis
    0.48
     Oculus
    0.47
    ន្ថ
    0.47
    ~$
    0.47
     Kawasaki
    0.44
     Avalon
    0.44
     Goa
    0.44
     Navarra
    0.44
     upstream
    0.43
     tuk
    0.43
    Activations Density 0.000%

    No Known Activations