© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1943
    Prev
    Next
    INDEX
    Explanations

    best followed by related words

    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
    ﺓ
    2.33
    ción
    2.31
     PR
    2.15
    ệt
    2.08
     GR
    2.05
     Io
    2.05
    ة
    2.00
    er
    1.96
    קו
    1.96
    गो
    1.96
    POSITIVE LOGITS
    CommonAncestor
    3.25
    Lists
    2.67
     deadliest
    2.61
    obranch
    2.48
     حالا
    2.46
    shortest
    2.45
    iegend
    2.41
    ǘ
    2.39
    ranged
    2.37
    ൂടെ
    2.35
    Activations Density 0.564%

    No Known Activations