© 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. 184684
    Prev
    Next
    INDEX
    Explanations

    foreign language

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

    financial security

    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
     again
    0.40
    ory
    0.40
     liters
    0.40
     niy
    0.40
     बढ़ाकर
    0.39
    娍
    0.39
    sc
    0.38
    ọn
    0.38
     Minimum
    0.38
     drips
    0.38
    POSITIVE LOGITS
    歡迎
    0.54
    INTa
    0.47
     بلکہ
    0.46
     بلکه
    0.46
    และ
    0.46
    ੍ਰ
    0.45
     possiamo
    0.45
     জনসাধারণের
    0.45
    ครอบ
    0.45
    ずっと
    0.44
    Activations Density 0.000%

    No Known Activations