© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85399
    Prev
    Next
    INDEX
    Explanations

    words ending in ot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -2.14
     unrelenting
    -2.13
     undeniably
    -2.13
     longstanding
    -2.11
     was
    -2.11
     nine
    -2.08
     and
    -2.06
     $
    -2.05
     can
    -1.98
     does
    -1.98
    POSITIVE LOGITS
     the
    3.22
    幛
    2.45
    踯
    2.39
    поги
    2.30
     alcune
    2.30
    稣
    2.28
    糴
    2.25
    ఽ
    2.20
     zoude
    2.19
    殽
    2.19
    Activations Density 0.040%

    No Known Activations