© 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. 223847
    Prev
    Next
    INDEX
    Explanations

    website, presenting, supports, most, support, just, now

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

    overview condition habit

    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
    เตอร์
    0.52
    ต์
    0.48
    0.47
     insistent
    0.47
    ジット
    0.47
     чемпиона
    0.46
    ติก
    0.46
     케
    0.46
    กลับ
    0.45
    지만
    0.45
    POSITIVE LOGITS
    FOUND
    0.51
     Qua
    0.49
    mc
    0.48
     Hospitals
    0.48
     Cloud
    0.48
    gaz
    0.47
    cloud
    0.46
     Birds
    0.46
     Forensic
    0.46
     cloud
    0.45
    Activations Density 0.000%

    No Known Activations