© 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. 59481
    Prev
    Next
    INDEX
    Explanations

    insurance, exemptions, login, renovations

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

    gpt and gpt 4

    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
    ion
    0.57
     ଚ
    0.55
    op
    0.53
    ic
    0.51
    ps
    0.49
    ig
    0.48
    ip
    0.48
    ens
    0.48
    itt
    0.47
    ini
    0.47
    POSITIVE LOGITS
    فاء
    0.49
    ار
    0.49
    産業
    0.48
     airflow
    0.48
     Oaks
    0.46
    勮
    0.46
     innov
    0.46
    汁
    0.45
     usuario
    0.44
    য়নের
    0.44
    Activations Density 0.000%

    No Known Activations