© 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. 16-GEMMASCOPE-2-RES-16K
    7. 44
    Prev
    Next
    INDEX
    Explanations

    forms of to be, able

    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_16_width_16k_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
    ع
    0.87
    ل
    0.83
    ه
    0.82
    ти
    0.82
    at
    0.79
    علم
    0.78
    ל
    0.77
    ו
    0.77
    ка
    0.70
    ת
    0.69
    POSITIVE LOGITS
     are
    0.82
    0.77
     is
    0.73
     à
    0.55
     ARE
    0.53
    রামর্শ
    0.49
     camped
    0.48
     società
    0.47
    ல்
    0.46
     able
    0.46
    Activations Density 3.093%

    No Known Activations