© 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. 120036
    Prev
    Next
    INDEX
    Explanations

    Nevada locations

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

    analysis, anomalies, evocative, media

    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
    ui
    0.51
    work
    0.45
     pendant
    0.44
    timed
    0.44
     Hamiltonian
    0.42
     caustic
    0.42
    io
    0.42
     >
    0.42
     flue
    0.42
    pe
    0.41
    POSITIVE LOGITS
    níci
    0.61
    }~
    0.54
    诌
    0.52
     Testimony
    0.47
    婍
    0.47
     Originally
    0.46
     usl
    0.46
    <0x98>
    0.46
    Cb
    0.45
     Nuestros
    0.45
    Activations Density 0.000%

    No Known Activations