© 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. 166272
    Prev
    Next
    INDEX
    Explanations

    offers and departures

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

    considering leaving or switching

    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
    Introdu
    0.50
    Бі
    0.48
    व
    0.46
    OSA
    0.46
     ава
    0.45
    ARIA
    0.45
    쭈
    0.44
    Prep
    0.43
    켈
    0.43
    Produto
    0.43
    POSITIVE LOGITS
     suitors
    0.61
     wechsel
    0.55
     allegiance
    0.54
     wechseln
    0.54
     relocation
    0.52
     ofertas
    0.52
     betray
    0.52
     relocate
    0.52
     loyalty
    0.51
     negotiation
    0.50
    Activations Density 0.079%

    No Known Activations