© 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. 148143
    Prev
    Next
    INDEX
    Explanations

    quarterback or research

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

    evidence-based thinking

    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
    Division
    0.50
    ו
    0.48
    洿
    0.42
    </td>
    0.42
     $<
    0.41
     awoke
    0.40
     Gesellschaft
    0.40
    Arist
    0.39
     prolongation
    0.39
    initions
    0.39
    POSITIVE LOGITS
    鸩
    0.54
     KAR
    0.53
     medicinal
    0.52
     marav
    0.50
     bungee
    0.50
     carp
    0.49
     Wonders
    0.49
     kar
    0.49
     निर्यात
    0.48
     सुमन
    0.48
    Activations Density 0.000%

    No Known Activations