© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 73081
    Prev
    Next
    INDEX
    Explanations

    both figures

    np_acts-logits-general · gemini-2.5-flash-lite

    family member

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ‪
    0.43
    <td>
    0.42
     recrutement
    0.42
     monotonically
    0.41
     ‪
    0.40
     raconte
    0.40
    ዻ
    0.40
    FXML
    0.40
    াণ্ড
    0.40
    (|\
    0.40
    POSITIVE LOGITS
    鿌
    0.50
    ları
    0.48
     Carolyn
    0.48
     Couleur
    0.47
    历史上
    0.47
    ert
    0.47
     Critique
    0.47
    橡胶
    0.47
     मिलाएं
    0.46
    龋
    0.46
    Activations Density 0.007%

    No Known Activations