© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79126
    Prev
    Next
    INDEX
    Explanations

    social media stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    0.47
     sapere
    0.43
     savoir
    0.43
    льності
    0.42
    scal
    0.42
    OfDay
    0.41
     Schl
    0.40
    ;
    0.40
     senso
    0.39
     santé
    0.38
    POSITIVE LOGITS
     Oekra
    0.44
    骄
    0.43
     näch
    0.42
    威胁
    0.41
     හි
    0.41
     ১২শ
    0.41
     चार
    0.40
     ሁለት
    0.40
     ज्वाइन
    0.40
    ienen
    0.39
    Activations Density 0.004%

    No Known Activations