© 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. 47151
    Prev
    Next
    INDEX
    Explanations

    variation depending on source

    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
    션
    0.49
     구
    0.45
    ด
    0.44
    mathcal
    0.44
     BOARD
    0.43
    된다
    0.42
    INK
    0.42
    জন
    0.42
    주
    0.41
     बांट
    0.41
    POSITIVE LOGITS
     menyelesaikan
    0.43
     yaşad
    0.42
     tweeted
    0.39
    <
    0.38
    <>();
    0.38
     supplying
    0.38
     terakhir
    0.37
    Providing
    0.37
    डेंट
    0.37
    、（
    0.36
    Activations Density 0.033%

    No Known Activations