© 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. 248196
    Prev
    Next
    INDEX
    Explanations

    astonished people on their hands

    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
    Ion
    0.45
    creating
    0.44
    </strong>
    0.43
    
    0.43
    TargetFramework
    0.42
    DURATION
    0.42
    burst
    0.41
     வளர்ச்சி
    0.41
    tetrahydro
    0.41
    <td>
    0.40
    POSITIVE LOGITS
     econôm
    0.53
     explan
    0.49
     varias
    0.48
     mandib
    0.48
     nautical
    0.47
     suya
    0.46
     laguna
    0.46
     beaches
    0.45
     ekonom
    0.45
     pengunjung
    0.45
    Activations Density 0.000%

    No Known Activations