© 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. 200069
    Prev
    Next
    INDEX
    Explanations

    Delta Phi

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

    limited, deviation, curiosity, bones, without

    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
     BasicContainer
    0.43
     общество
    0.43
     सोसायटी
    0.42
     robot
    0.42
    Ւ
    0.41
     Lieu
    0.41
    Seq
    0.40
    ᱞ
    0.39
    uniqueItems
    0.39
    /"><
    0.39
    POSITIVE LOGITS
     dokładnie
    0.46
    持ち
    0.46
     tiresome
    0.43
    kond
    0.43
    wiring
    0.42
     terus
    0.42
     genauso
    0.41
     ફક્ત
    0.41
    atud
    0.41
    ্য
    0.41
    Activations Density 0.000%

    No Known Activations