© 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. 250892
    Prev
    Next
    INDEX
    Explanations

    my, your, from, here

    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
     ዘዴ
    0.54
    殚
    0.54
     作業
    0.51
    ⴹ
    0.50
    堝
    0.50
     ដ
    0.49
     คอม
    0.49
    ៧
    0.48
     డ
    0.48
    dosage
    0.47
    POSITIVE LOGITS
     into
    0.46
    خ
    0.46
     maintenance
    0.43
     wants
    0.43
     guesses
    0.42
     simplifies
    0.42
     retained
    0.42
    c
    0.42
     I
    0.41
    x
    0.40
    Activations Density 0.000%

    No Known Activations