© 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. 228647
    Prev
    Next
    INDEX
    Explanations

    rights, are, make, Range, is, non

    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
    infused
    0.46
    튜
    0.44
     Lembrando
    0.43
     Sci
    0.42
     Romania
    0.42
    인지
    0.42
    IR
    0.41
    땜
    0.41
    foreach
    0.41
    that
    0.41
    POSITIVE LOGITS
    ক
    0.49
     generalmente
    0.48
     overshadow
    0.46
     después
    0.45
     နောက်
    0.44
    )^*
    0.44
     formaldehyde
    0.43
     прида
    0.43
     embora
    0.42
     ejerc
    0.42
    Activations Density 0.001%

    No Known Activations