© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54379
    Prev
    Next
    INDEX
    Explanations

    Startup Programs

    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
     equivari
    0.38
     واقعہ
    0.38
    一定的
    0.38
     относя
    0.37
     pedibusque
    0.37
     levando
    0.37
     때는
    0.37
     접
    0.36
    很大的
    0.36
     unfilled
    0.36
    POSITIVE LOGITS
     trailed
    0.45
     nurs
    0.40
     naturally
    0.38
    نګ
    0.38
     Islands
    0.38
     marsh
    0.38
    sgem
    0.38
     railway
    0.37
    äv
    0.37
     proved
    0.37
    Activations Density 0.000%

    No Known Activations