© 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. 107630
    Prev
    Next
    INDEX
    Explanations

    Enjoy music or choosing checkbox

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

    AI, usage, communication, 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
    5
    0.52
    7
    0.52
    inal
    0.50
    ing
    0.50
    imal
    0.49
    ای
    0.49
    4
    0.48
    ema
    0.47
    amenti
    0.47
    дування
    0.47
    POSITIVE LOGITS
    ণ্ঠে
    0.60
     IGF
    0.46
     savun
    0.45
     OPCODE
    0.45
     CME
    0.44
    ঠিত
    0.44
    孅
    0.44
    ணும்
    0.44
     Streit
    0.43
     Qxh
    0.43
    Activations Density 0.000%

    No Known Activations