© 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. 231423
    Prev
    Next
    INDEX
    Explanations

    family caregiver

    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
    ⸜
    0.44
     asympt
    0.42
     ist
    0.42
    ×
    0.42
     einschließlich
    0.40
    🖥
    0.40
    ↦
    0.40
     λ
    0.40
     applic
    0.39
     sarà
    0.39
    POSITIVE LOGITS
    ok
    0.51
    dist
    0.50
    {},
    0.50
    UR
    0.48
    alak
    0.48
    akwa
    0.48
    op
    0.47
    ళ్ళ
    0.47
    Tarea
    0.47
    Estas
    0.47
    Activations Density 0.001%

    No Known Activations