© 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. 183627
    Prev
    Next
    INDEX
    Explanations

    email address

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

    perception, screen, String, mode

    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
    RL
    0.56
    RS
    0.48
    ZL
    0.48
    Finding
    0.48
    rile
    0.48
    ikten
    0.48
    勐
    0.48
    HI
    0.47
     प्रती
    0.46
     dismay
    0.46
    POSITIVE LOGITS
     гэ
    0.49
     불구하고
    0.44
    चालित
    0.43
    ])
    0.43
     স্বীকৃতি
    0.41
     RoutedEventArgs
    0.41
     여섯
    0.41
    ]})
    0.40
    ]){
    0.40
    نيف
    0.39
    Activations Density 0.000%

    No Known Activations