© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1257
    Prev
    Next
    INDEX
    Explanations

    of [concept]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    циони
    1.84
    जिब
    1.66
    𝐚
    1.60
    izmus
    1.56
    ers
    1.53
    tei
    1.49
    इज
    1.49
    cede
    1.48
    kerja
    1.48
    वर्ल्ड
    1.45
    POSITIVE LOGITS
    DLJ
    2.04
     $-$
    1.93
    QRSTUVWXYZ
    1.92
    accharides
    1.82
     בלי
    1.80
     בו
    1.73
    IQUE
    1.68
    quard
    1.68
     وقد
    1.67
     iw
    1.66
    Activations Density 0.403%

    No Known Activations