© 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-16K
    7. 4825
    Prev
    Next
    INDEX
    Explanations

    audience specification

    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_16k_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
    </b>
    0.44
    *',
    0.40
    name
    0.39
    checker
    0.39
     ಸ್ನೇಹಿತ
    0.39
    +',
    0.38
    ของผู้
    0.38
    c
    0.37
     ಇತರ
    0.37
    Checker
    0.37
    POSITIVE LOGITS
    向けの
    0.50
    向け
    0.47
     അവരുടെ
    0.44
     Mik
    0.43
     kust
    0.43
    という意味
    0.42
    ("")]
    0.41
     ඔවුන්
    0.41
     Treasury
    0.41
     dosis
    0.41
    Activations Density 0.357%

    No Known Activations