© 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. 209097
    Prev
    Next
    INDEX
    Explanations

    smoked baby

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

    expectation and rate of change

    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
    坻
    0.47
     Citrix
    0.44
     HAS
    0.43
     цели
    0.43
    稜
    0.43
    </tbody>
    0.42
    xi
    0.42
    lipper
    0.42
     પોતા
    0.42
    蹌
    0.42
    POSITIVE LOGITS
    Кон
    0.51
    ק
    0.49
    ofstream
    0.47
     substituir
    0.46
    utiliser
    0.46
     anlamına
    0.45
    ט
    0.45
    these
    0.44
    recording
    0.43
    FEC
    0.43
    Activations Density 0.012%

    No Known Activations