© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85828
    Prev
    Next
    INDEX
    Explanations

    past tense verbs in reports

    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
     and
    -3.34
    ?"
    -2.36
     in
    -2.36
     impeccable
    -2.34
     with
    -2.30
     after
    -2.30
     when
    -2.25
     specific
    -2.20
     by
    -2.19
     at
    -2.06
    POSITIVE LOGITS
    镚
    2.72
    鲣
    2.44
    蠓
    2.42
    锨
    2.39
    秶
    2.25
    ፨
    2.22
    ܆
    2.17
    鸸
    2.17
    %;
    2.17
    {})
    2.16
    Activations Density 0.413%

    No Known Activations