© 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. 44289
    Prev
    Next
    INDEX
    Explanations

    avoiding excess and negative feelings

    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
    nonzero
    0.44
    รวจ
    0.43
     incompar
    0.41
    "]},{"
    0.40
     훨
    0.39
     ដ
    0.38
     করিয়াছিলেন
    0.37
    훨
    0.36
    Smiling
    0.36
     দিয়া
    0.36
    POSITIVE LOGITS
     excessive
    1.05
     Excessive
    0.98
    Excess
    0.94
    excess
    0.93
     eccess
    0.88
     exces
    0.86
     overkill
    0.86
     excess
    0.84
     Excess
    0.84
     overly
    0.80
    Activations Density 0.135%

    No Known Activations