© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 35243
    Prev
    Next
    INDEX
    Explanations

    Smollett and county

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

    aiming for neutrality in interactions

    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
     ವಿಷಯ
    0.46
     Jdbc
    0.46
    ্না
    0.45
     *,
    0.43
    се
    0.43
    ,":
    0.43
    _{,
    0.42
    리스
    0.42
    као
    0.42
     सुनो
    0.42
    POSITIVE LOGITS
     locking
    0.54
     collecting
    0.44
    抻
    0.44
     exhaust
    0.43
     coughing
    0.43
     Locking
    0.43
     yog
    0.42
     সাহস
    0.42
     Bucs
    0.42
     inspiration
    0.41
    Activations Density 0.000%

    No Known Activations