© 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. 180698
    Prev
    Next
    INDEX
    Explanations

    exposure time

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

    FM radio

    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
    ，
    0.47
     Target
    0.41
     স্মরণ
    0.41
     Targeting
    0.41
    كلمنا
    0.41
     والر
    0.40
    াহি
    0.40
    tsc
    0.40
     ricordare
    0.40
    Oste
    0.39
    POSITIVE LOGITS
     컴퓨터
    0.51
     Hitler
    0.47
    ῳ
    0.46
    เชสเตอร์
    0.44
     mathemat
    0.43
     computers
    0.43
     abomin
    0.42
     boobs
    0.42
     initiating
    0.42
     causation
    0.42
    Activations Density 0.003%

    No Known Activations