© 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. 8130
    Prev
    Next
    INDEX
    Explanations

    topics after "on"

    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
     thei
    0.40
    zeption
    0.38
     কিছু
    0.38
    ្ឋ
    0.38
    a
    0.37
     ihrer
    0.37
     leur
    0.34
     Polda
    0.34
    ominator
    0.34
     त्यांचे
    0.33
    POSITIVE LOGITS
     assuntos
    0.44
    럼
    0.38
    \}_{
    0.38
    ]_{
    0.36
    ücklich
    0.36
     соответственно
    0.35
     assunto
    0.35
    늄
    0.35
     проблема
    0.34
     probabilidad
    0.34
    Activations Density 0.103%

    No Known Activations