© 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. 23242
    Prev
    Next
    INDEX
    Explanations

    author, resolved, winner

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

    especially when given

    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
     ~\
    0.53
    、
    0.53
     、
    0.53
    س
    0.52
     Coupled
    0.49
    می
    0.45
    偵
    0.45
    este
    0.45
    <sup>
    0.44
    _{+}^{
    0.44
    POSITIVE LOGITS
    ว์
    0.49
    trombone
    0.47
     despicable
    0.47
     signifies
    0.46
    ciamo
    0.46
    ಾತ
    0.46
     आत
    0.46
     ineffective
    0.46
     indented
    0.46
     metallic
    0.46
    Activations Density 0.000%

    No Known Activations