© 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. 149277
    Prev
    Next
    INDEX
    Explanations

    or connecting words

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

    waiting for a response

    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
    (,
    0.51
    t
    0.51
     NPV
    0.49
     Biochem
    0.45
    tl
    0.45
    None
    0.44
    !।
    0.44
    
    0.43
    __(
    0.43
    nm
    0.43
    POSITIVE LOGITS
    ڈ
    0.49
     있다는
    0.48
     extrémités
    0.48
     emblematic
    0.48
     reconnect
    0.47
     можуть
    0.45
     nabíz
    0.45
     soutenir
    0.44
     offrent
    0.44
     rapproche
    0.44
    Activations Density 0.000%

    No Known Activations