© 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. 148247
    Prev
    Next
    INDEX
    Explanations

    countersadvocatedresidentfund

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

    okay, sometimes, might

    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
     reunion
    0.47
     messages
    0.46
    朲
    0.45
     emerging
    0.44
     uncertainty
    0.44
     rebellion
    0.44
     logout
    0.43
     op
    0.43
     bukan
    0.42
    гляд
    0.42
    POSITIVE LOGITS
     Lipp
    0.50
    bacteria
    0.49
     ಉದ್ದ
    0.48
    sama
    0.47
    apare
    0.46
    OPES
    0.46
    砜
    0.46
    na
    0.46
    OURCE
    0.46
     シャツ
    0.46
    Activations Density 0.002%

    No Known Activations