© 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. 133512
    Prev
    Next
    INDEX
    Explanations

    looked after

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

    BPD, burnout, missing, repeated

    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
     yì
    0.49
    ïque
    0.48
    璟
    0.47
     conceded
    0.46
    逺
    0.45
     convo
    0.44
     duidelijk
    0.43
    లీ
    0.42
    صيل
    0.42
    
    0.42
    POSITIVE LOGITS
    november
    0.52
    novu
    0.50
    european
    0.49
    comparing
    0.48
    transform
    0.48
    with
    0.48
    affron
    0.48
    domain
    0.47
    navigation
    0.47
    requirements
    0.47
    Activations Density 0.000%

    No Known Activations