© 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. 16-GEMMASCOPE-2-RES-262K
    7. 105941
    Prev
    Next
    INDEX
    Explanations

    conditional or hypothetical statements

    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_16_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
    α
    0.55
    па
    0.54
    か
    0.54
    не
    0.54
    ine
    0.53
    ě
    0.53
    έ
    0.53
    i
    0.52
    ي
    0.52
    е
    0.52
    POSITIVE LOGITS
     ಬಾರಿ
    0.56
    OLYBD
    0.54
     করিয়াছেন
    0.53
     আরবি
    0.52
     arbitrary
    0.49
     ಸರ್
    0.49
    rypted
    0.49
     المثلث
    0.49
     llamas
    0.49
     crescent
    0.49
    Activations Density 0.032%

    No Known Activations