© 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. 31751
    Prev
    Next
    INDEX
    Explanations

    "From Wikipedia, the free encyclopedia"

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

    reliance on, rely on, limit

    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
    eringen
    0.44
    ende
    0.40
    ง
    0.40
     Transaction
    0.39
    ì
    0.39
    wein
    0.39
    esis
    0.38
    են
    0.38
    වු
    0.38
     \
    0.38
    POSITIVE LOGITS
    బాద్
    0.46
    コーデ
    0.45
     Eyre
    0.45
     electr
    0.45
     coordinating
    0.44
     außerdem
    0.43
     быстрее
    0.43
     electrified
    0.43
     permettent
    0.43
    শনাল
    0.42
    Activations Density 0.001%

    No Known Activations