© 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-262K
    7. 12072
    Prev
    Next
    INDEX
    Explanations

    conditional logic `if` statements

    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
     με
    0.47
     Τ
    0.46
     গলা
    0.39
     Ι
    0.38
     Α
    0.37
    τε
    0.36
     ο
    0.35
     Μ
    0.35
     ι
    0.34
    Τ
    0.34
    POSITIVE LOGITS
    assumption
    0.45
     എന്നാൽ
    0.42
     അല്ലെങ്കിൽ
    0.41
    ี
    0.39
    存档备份
    0.39
    istic
    0.38
    पाकिस्तान
    0.38
    but
    0.38
     لكن
    0.38
     perspect
    0.37
    Activations Density 0.070%

    No Known Activations