© 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-65K
    7. 51963
    Prev
    Next
    INDEX
    Explanations

    falling or light

    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_65k_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
    THROW
    0.42
    காற்று
    0.41
     θε
    0.39
    ȇ
    0.39
     ثلاثه
    0.39
    굶
    0.38
    ਸ਼
    0.38
    lycerin
    0.37
    țiunea
    0.37
     oraș
    0.37
    POSITIVE LOGITS
    Photograph
    0.45
    paid
    0.43
     पड़ी
    0.43
     redd
    0.43
    падает
    0.43
    落ち
    0.41
     fallen
    0.41
     falling
    0.41
     fell
    0.40
    落
    0.40
    Activations Density 0.006%

    No Known Activations