© 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. 74526
    Prev
    Next
    INDEX
    Explanations

    we believe

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

    Historically, several, face

    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
    a
    0.57
    Wikipedia
    0.46
    cool
    0.46
    characteristic
    0.45
     setbacks
    0.45
    cross
    0.44
    improvements
    0.44
    change
    0.44
    mour
    0.43
    )
    0.43
    POSITIVE LOGITS
     Cá
    0.50
    цією
    0.50
    
    0.50
    ţia
    0.49
     Idam
    0.47
     relais
    0.47
     concat
    0.46
    Ἠ
    0.46
     Lei
    0.45
    ționale
    0.45
    Activations Density 0.002%

    No Known Activations