© 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. 176088
    Prev
    Next
    INDEX
    Explanations

    history of computing

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

    depending on situations

    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
    בה
    0.53
    בר
    0.46
    ג
    0.46
    Sandbox
    0.45
     باعث
    0.45
    Sending
    0.44
    
    0.44
    ویی
    0.43
    ਆ
    0.43
    Outputs
    0.43
    POSITIVE LOGITS
    ；
    0.48
     ancien
    0.46
     invertible
    0.46
     Historically
    0.45
     testify
    0.43
     rentals
    0.42
     China
    0.42
     Malta
    0.42
     Freud
    0.41
     Taiwan
    0.41
    Activations Density 0.001%

    No Known Activations