© 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. 14368
    Prev
    Next
    INDEX
    Explanations

    call it, call for, call out

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

    call followed by someone or for

    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
     Geschwindigkeit
    0.75
    <unused2177>
    0.65
    تيب
    0.64
     immensely
    0.63
     darstellen
    0.63
    鍱
    0.63
     dargestellt
    0.61
     Darstellung
    0.60
     shew
    0.59
     longitudinale
    0.59
    POSITIVE LOGITS
    call
    1.20
    Call
    1.20
     call
    1.09
    calling
    1.02
    呼
    1.01
    Calling
    0.99
    కు
    0.97
     호출
    0.95
    Calls
    0.93
    呼び
    0.92
    Activations Density 0.068%

    No Known Activations