© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45646
    Prev
    Next
    INDEX
    Explanations

    general introduction/explanation

    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_262k_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
     tissues
    0.43
    rowth
    0.42
     つ
    0.41
     metabolic
    0.41
     marines
    0.41
    ulates
    0.41
    r
    0.40
    р
    0.40
    ii
    0.40
    ar
    0.39
    POSITIVE LOGITS
    地点
    0.48
     grundsätzlich
    0.48
     عند
    0.47
     méthode
    0.45
     Üniversitesi
    0.45
    할
    0.45
    蒂
    0.45
    विद्या
    0.44
     Ünivers
    0.44
    一般
    0.43
    Activations Density 0.005%

    No Known Activations