© 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. 184223
    Prev
    Next
    INDEX
    Explanations

    tie things

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

    actively dismantle, probability distribution, consistently demonstrates

    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
    লাকে
    0.45
     exclusivement
    0.44
    قامة
    0.44
    )-\
    0.43
    十六章
    0.42
    )~
    0.40
     لإ
    0.40
    ள்ப
    0.40
    ));
    0.40
     以及
    0.40
    POSITIVE LOGITS
    ask
    0.58
     repert
    0.56
    ist
    0.50
    aker
    0.49
    जो
    0.49
    weapon
    0.49
    ito
    0.48
    TH
    0.48
    itas
    0.48
    ies
    0.47
    Activations Density 0.000%

    No Known Activations