© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13754
    Prev
    Next
    INDEX
    Explanations

    press release or wire service

    np_acts-logits-general · gemini-2.5-flash-lite

    beginning of document or body

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    2
    0.67
    4
    0.66
    3
    0.64
    6
    0.50
    7
    0.50
    IR
    0.48
    VR
    0.48
    1
    0.47
    8
    0.47
    CT
    0.46
    POSITIVE LOGITS
     )}$
    0.46
     বঙ্গের
    0.45
    біць
    0.45
     voids
    0.44
     cang
    0.44
     régl
    0.43
    াইবার
    0.43
     tumours
    0.43
     eventuali
    0.43
     zmniejs
    0.41
    Activations Density 0.000%

    No Known Activations