© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2935
    Prev
    Next
    INDEX
    Explanations

    decline, declining

    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_34/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
     inept
    -1.33
    あげる
    -1.14
     gleaming
    -1.13
     blazing
    -1.12
     deudas
    -1.10
     มัน
    -1.10
    ឵
    -1.09
    ChrTalk
    -1.07
    StoryboardSegue
    -1.07
     despicable
    -1.06
    POSITIVE LOGITS
     or
    1.58
     in
    1.35
     from
    1.30
     of
    1.30
    \
    1.16
     poniżej
    1.06
     as
    1.05
    $
    1.01
     to
    0.98
     ".";
    0.96
    Activations Density 0.032%

    No Known Activations