© 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. 40-GEMMASCOPE-2-RES-262K
    7. 221464
    Prev
    Next
    INDEX
    Explanations

    Big Bang plasma and photons

    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_40_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
    趸
    0.40
     모델
    0.40
     நார்
    0.39
    áci
    0.39
    collapsed
    0.38
    संद
    0.38
     ආර
    0.38
    ಂಕ
    0.37
    属
    0.37
     அள
    0.37
    POSITIVE LOGITS
     decouple
    0.44
     decoupling
    0.44
     temperatures
    0.41
     plasma
    0.40
     licht
    0.40
     photons
    0.39
     φω
    0.38
     drops
    0.38
     universe
    0.38
     bary
    0.37
    Activations Density 0.011%

    No Known Activations