© 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. 202870
    Prev
    Next
    INDEX
    Explanations

    easily include required

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

    needs, on, this, supports

    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
    ники
    0.51
    никами
    0.49
     рассказа
    0.47
    крови
    0.46
    캅
    0.46
    níku
    0.45
    ానని
    0.44
    యా
    0.44
    Elems
    0.42
    级的
    0.42
    POSITIVE LOGITS
    un
    0.48
     table
    0.47
    선
    0.47
     flute
    0.45
     버
    0.45
     母
    0.44
    合格
    0.44
     snap
    0.43
     ms
    0.43
     lt
    0.43
    Activations Density 0.001%

    No Known Activations