© 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. 154995
    Prev
    Next
    INDEX
    Explanations

    Crater, waters, available

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

    units and comparisons

    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
     us
    0.54
     outpouring
    0.54
    )
    0.53
     exot
    0.52
     luncheon
    0.51
     HIPAA
    0.50
    S
    0.50
     sortie
    0.49
     anun
    0.49
     dollar
    0.49
    POSITIVE LOGITS
    getWidth
    0.50
     فوټبال
    0.49
    ార్లు
    0.47
    žite
    0.45
    寘
    0.44
    的关系
    0.44
    ভূত
    0.43
    getId
    0.43
    getAll
    0.43
    setSelected
    0.43
    Activations Density 0.001%

    No Known Activations