© 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. 136488
    Prev
    Next
    INDEX
    Explanations

    While violet is more, sky is blue

    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
    ٹ
    0.63
     খাজ
    0.50
    țion
    0.48
    łow
    0.47
    ünüz
    0.47
     käytt
    0.47
    𝔰
    0.47
     haszn
    0.47
     Kidney
    0.46
     MAGAZ
    0.46
    POSITIVE LOGITS
     sentient
    0.47
    .]:
    0.41
     since
    0.39
     practitioners
    0.38
    ]<
    0.37
     reserve
    0.36
    
    0.35
     opaque
    0.35
     under
    0.34
     cohort
    0.34
    Activations Density 0.001%

    No Known Activations