© 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. 39941
    Prev
    Next
    INDEX
    Explanations

    bombs fell

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

    walking on eggshells, used in, intermediate -

    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
     madad
    0.44
    ن
    0.44
     wichtigen
    0.43
     ajudar
    0.43
     concernant
    0.43
     causas
    0.42
     aiut
    0.42
     ayud
    0.42
     đừng
    0.41
     innehåller
    0.41
    POSITIVE LOGITS
     irradiated
    0.47
     honed
    0.45
    =[],
    0.43
    orted
    0.42
     ಶೆ
    0.42
     taxed
    0.41
     programmed
    0.40
    rnn
    0.39
     ವಿಶ
    0.39
    oretum
    0.39
    Activations Density 0.000%

    No Known Activations