© 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. 128713
    Prev
    Next
    INDEX
    Explanations

    street photography

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

    targeted skill improvement

    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
     arasındaki
    0.51
    lcc
    0.50
     வைத்த
    0.49
    lhe
    0.48
     insgesamt
    0.48
    </tbody>
    0.46
     Übersicht
    0.45
     لحظ
    0.45
     basiert
    0.45
     Zwischen
    0.44
    POSITIVE LOGITS
    Jf
    0.53
     be
    0.51
    Rather
    0.51
    ǃ
    0.48
    be
    0.47
    ༨
    0.46
     प्रौ
    0.46
     права
    0.42
     во
    0.42
    åt
    0.42
    Activations Density 0.000%

    No Known Activations