© 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. 153840
    Prev
    Next
    INDEX
    Explanations

    brow pencil

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

    serious tone

    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
    塚
    0.48
     mitochond
    0.45
     CERN
    0.43
    ≧
    0.43
    Casino
    0.42
    <td>
    0.42
    Some
    0.42
     Precambrian
    0.41
     spectrosc
    0.41
    Putin
    0.41
    POSITIVE LOGITS
     مذہ
    0.47
     तरीके
    0.47
     जहां
    0.46
     યોગ્ય
    0.45
     esforços
    0.45
    倾
    0.44
     அவள்
    0.44
     ढंग
    0.43
     класи
    0.43
     зокрема
    0.43
    Activations Density 0.000%

    No Known Activations