© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 1546
    Prev
    Next
    INDEX
    Explanations

    not followed by condition or negation

    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_13_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
    ἆ
    2.69
     polypes
    2.63
    vine
    2.41
    achtree
    2.33
    निश्ड
    2.29
    squareup
    2.28
    fees
    2.25
     неравен
    2.24
    vina
    2.20
     mặt
    2.19
    POSITIVE LOGITS
    tingham
    2.31
    ంటర్
    2.30
    榔
    2.26
    ต์
    2.26
    zsche
    2.10
    withstanding
    2.07
    ────────────────
    2.06
    ের
    2.05
     necessarily
    2.03
     ";
    2.01
    Activations Density 0.401%

    No Known Activations