© 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. 156476
    Prev
    Next
    INDEX
    Explanations

    specific follow-ups

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

    pressure units like MPa

    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
    nements
    0.51
    美國
    0.47
    سين
    0.45
    ثم
    0.45
    玽
    0.45
    ClrBit
    0.45
    كري
    0.44
    يره
    0.44
    猀
    0.44
    طات
    0.43
    POSITIVE LOGITS
     solution
    0.51
    <unused60>
    0.48
    IFUL
    0.47
    romatic
    0.47
     रत
    0.46
     kW
    0.45
     multifunctional
    0.44
     शानदार
    0.44
     macrom
    0.44
     machined
    0.44
    Activations Density 0.000%

    No Known Activations