© 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. 136070
    Prev
    Next
    INDEX
    Explanations

    running their own

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

    running GUI, requires government, server is

    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
    alit
    0.48
    arra
    0.46
    leding
    0.45
    alp
    0.44
    apabb
    0.43
     ग्ले
    0.43
    ି
    0.43
    aldi
    0.43
    Semif
    0.42
    agel
    0.42
    POSITIVE LOGITS
     indetermin
    0.53
     又
    0.52
     covari
    0.49
     toil
    0.48
    Reactor
    0.47
     pernicious
    0.47
     exported
    0.46
     fission
    0.46
     thorium
    0.46
     Reactor
    0.46
    Activations Density 0.001%

    No Known Activations