© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6365
    Prev
    Next
    INDEX
    Explanations

    abstract qualities and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite

    qualities and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    嚿
    0.31
     tn
    0.30
    )\
    0.29
     oid
    0.29
     হইত
    0.29
     ẞ
    0.29
     লিখিতে
    0.28
     উক্ত
    0.28
     irritating
    0.28
     contribution
    0.27
    POSITIVE LOGITS
     и
    0.39
    และความ
    0.38
     आणि
    0.37
     và
    0.35
     και
    0.35
     galore
    0.35
     અને
    0.35
    पूर्ण
    0.34
     و
    0.33
     और
    0.32
    Activations Density 0.409%

    No Known Activations