© 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. 79718
    Prev
    Next
    INDEX
    Explanations

    time, lunch, Gogh, impacts, clothes, both, Kane, years, I, now

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

    describing relationships or situations

    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
    鈑
    0.55
    钣
    0.49
     несколь
    0.43
    ITAR
    0.42
     towed
    0.41
     লাগবে
    0.41
    PIRED
    0.41
     здравоохра
    0.41
    अ
    0.40
    Backward
    0.39
    POSITIVE LOGITS
     href
    0.46
     पति
    0.45
    ండు
    0.44
    most
    0.40
     underpinning
    0.40
    adiya
    0.39
    hk
    0.39
    chung
    0.39
     marido
    0.39
     elb
    0.39
    Activations Density 0.000%

    No Known Activations