© 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. 49744
    Prev
    Next
    INDEX
    Explanations

    places with distances or times

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

    how many times X goes into Y

    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
     Explained
    0.42
     Computational
    0.42
     finale
    0.40
    ကြောင်း
    0.39
     falsch
    0.39
     finals
    0.39
     errorMessage
    0.39
     =-\
    0.38
    ี่ยง
    0.38
     μαγγ
    0.38
    POSITIVE LOGITS
    parte
    0.52
    윳
    0.43
    Hunt
    0.41
    Appellant
    0.38
    ҳои
    0.37
     бюджета
    0.37
    Ḥ
    0.37
    ུ
    0.37
    🛍
    0.37
     هیچ
    0.36
    Activations Density 0.000%

    No Known Activations