© 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. 11797
    Prev
    Next
    INDEX
    Explanations

    , age or order

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

    as e

    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
    ewöhn
    0.48
    揩
    0.45
    Jetzt
    0.45
     забруд
    0.44
    KURZ
    0.44
    长期
    0.43
     Wochschr
    0.43
    普通的
    0.43
    zonego
    0.43
    ികിത്സ
    0.42
    POSITIVE LOGITS
     e
    0.70
     p
    0.68
     v
    0.67
     i
    0.67
     x
    0.65
     _
    0.65
     _,
    0.63
    x
    0.61
     d
    0.60
     q
    0.60
    Activations Density 0.000%

    No Known Activations