© 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. 234905
    Prev
    Next
    INDEX
    Explanations

    Javed Mahesh Padilla Helios

    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
    ㊙
    0.46
    қда
    0.44
    监狱
    0.44
    亚洲
    0.42
     측정
    0.41
    ზ
    0.41
    遵
    0.40
    وية
    0.40
    病毒
    0.40
    configurable
    0.39
    POSITIVE LOGITS
     Javed
    0.50
    tion
    0.46
     Mahesh
    0.44
     Padilla
    0.44
     Helios
    0.44
    謐
    0.43
     Gregorio
    0.43
    IES
    0.43
     Juni
    0.43
     Werbung
    0.42
    Activations Density 0.000%

    No Known Activations