© 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. 31-GEMMASCOPE-2-RES-65K
    7. 9315
    Prev
    Next
    INDEX
    Explanations

    title tags

    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_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
     varnish
    0.28
     powdered
    0.27
     tượng
    0.27
     pyridine
    0.27
     puffer
    0.27
    \
    0.27
     residues
    0.27
     brown
    0.26
     varn
    0.26
     oxen
    0.26
    POSITIVE LOGITS
    ife
    0.32
    ოლ
    0.31
    ">(</
    0.30
    ">⁡</
    0.30
    𝙰
    0.29
     nirvach
    0.28
    junctive
    0.28
    Ⲣ
    0.28
     zweite
    0.28
     භාවිතා
    0.28
    Activations Density 0.004%

    No Known Activations