© 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. 223856
    Prev
    Next
    INDEX
    Explanations

    spiritual goats

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

    prompt instructions

    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
    is
    0.51
    ター
    0.50
    నె
    0.50
    ре
    0.48
    두
    0.47
    March
    0.47
    ی
    0.46
    да
    0.46
    ラ
    0.45
     Coppola
    0.45
    POSITIVE LOGITS
     dizi
    0.52
     dowol
    0.51
     nonzero
    0.50
     folgen
    0.47
     anzeigen
    0.47
     ibang
    0.47
     supple
    0.46
     był
    0.46
     rozpoczę
    0.46
     podob
    0.45
    Activations Density 0.001%

    No Known Activations