© 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. 22736
    Prev
    Next
    INDEX
    Explanations

    how awards won

    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
    žu
    0.44
    䉽
    0.43
     Krzysz
    0.42
    𝓪
    0.41
    ḳ
    0.41
    cknowledg
    0.41
    ❖
    0.41
    ถ้า
    0.40
    ḵ
    0.40
    ösung
    0.39
    POSITIVE LOGITS
     congruence
    0.43
     adherence
    0.42
     doubles
    0.41
    過ご
    0.40
     bloc
    0.40
     concept
    0.39
     reached
    0.39
     dilapidated
    0.39
     lame
    0.38
     pequenas
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.