© 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. 193905
    Prev
    Next
    INDEX
    Explanations

    employment or intervention

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

    padre rico, padre pobre; involves, unlike

    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
     Erinner
    0.49
    ल
    0.49
    ir
    0.47
     Wege
    0.46
    ні
    0.46
     Tiet
    0.46
     suchen
    0.45
    точной
    0.44
     tissues
    0.43
     Keine
    0.43
    POSITIVE LOGITS
     discharging
    0.45
    麿
    0.44
    逹
    0.44
    竄
    0.44
    鵜
    0.43
     menyiapkan
    0.42
     اجر
    0.42
    ECT
    0.41
    饉
    0.41
     HERO
    0.40
    Activations Density 0.007%

    No Known Activations