© 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. 1866
    Prev
    Next
    INDEX
    Explanations

    other followed by nouns

    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
    1.58
     unfold
    1.42
     mutable
    1.37
    ুন
    1.31
    ْنَ
    1.26
    (_.
    1.26
    ותו
    1.25
     loosely
    1.25
    icked
    1.24
    fraction
    1.24
    POSITIVE LOGITS
    árez
    1.84
    chyné
    1.53
    इ
    1.51
     nombreux
    1.50
    工程
    1.48
    igueur
    1.47
    ോധ
    1.46
     siguen
    1.46
     principaux
    1.45
    ité
    1.44
    Activations Density 0.144%

    No Known Activations