© 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. 58323
    Prev
    Next
    INDEX
    Explanations

    vector math and object properties

    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
    agun
    0.45
    FromBody
    0.44
    jj
    0.43
    θ
    0.42
    полне
    0.42
    ONG
    0.42
    Sov
    0.42
    }^{*}=\
    0.41
    touchstart
    0.41
    bj
    0.40
    POSITIVE LOGITS
     gerade
    0.47
     Breach
    0.47
     yüksek
    0.46
     meines
    0.45
     şu
    0.44
     Schach
    0.44
     wirklich
    0.44
     Disputes
    0.44
     lassen
    0.43
     Hubert
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.