© 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. 34-GEMMASCOPE-RES-131K
    7. 48963
    Prev
    Next
    INDEX
    Explanations

    I or we followed by a verb

    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
    ríklad
    -0.84
    пара
    -0.84
    ignement
    -0.83
    期刊
    -0.82
     км
    -0.81
     Chang
    -0.81
    разви
    -0.81
    default
    -0.79
    chin
    -0.79
     деца
    -0.79
    POSITIVE LOGITS
     shall
    1.70
     cannot
    1.38
     have
    1.27
     should
    1.22
     hardly
    1.13
     myself
    1.03
     know
    1.02
     scarcely
    1.02
     knew
    0.98
     ourselves
    0.96
    Activations Density 0.014%

    No Known Activations