© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54413
    Prev
    Next
    INDEX
    Explanations

    disco optico

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    㳓
    0.52
    т
    0.50
    ק
    0.49
     శరీర
    0.47
    스터
    0.47
     fraî
    0.46
    신
    0.46
    लक्ष
    0.45
     ምልክ
    0.45
    Idioma
    0.44
    POSITIVE LOGITS
    0.47
    ereich
    0.42
    arith
    0.41
    aram
    0.41
    amay
    0.40
     GND
    0.39
     barely
    0.38
     spiced
    0.38
    diverse
    0.37
     leapt
    0.37
    Activations Density 0.008%

    No Known Activations