© 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. 169335
    Prev
    Next
    INDEX
    Explanations

    minute game

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

    explaining or requiring something

    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
    떳
    0.52
    ્ય
    0.45
    "।
    0.43
     viscous
    0.43
    )‏
    0.41
    一张
    0.41
     trwa
    0.40
    それが
    0.40
     disgraceful
    0.40
    一張
    0.40
    POSITIVE LOGITS
    ளையும்
    0.51
     pemb
    0.44
     ভরা
    0.43
    ians
    0.43
     മു
    0.43
     និង
    0.43
     (&
    0.43
    timed
    0.43
     प्ल
    0.42
     दैन
    0.42
    Activations Density 0.003%

    No Known Activations