© 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. 18785
    Prev
    Next
    INDEX
    Explanations

    flight stops

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

    reflective character and observation

    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
    ス
    0.64
    お
    0.52
    ミ
    0.51
    一
    0.47
    ча
    0.47
    ᾧ
    0.46
    ウ
    0.45
    {
    0.44
    талия
    0.43
    л
    0.43
    POSITIVE LOGITS
     كلمه
    0.54
     konfl
    0.53
     تجاوز
    0.52
     تعد
    0.51
     انصاف
    0.51
     lauf
    0.51
    버스
    0.50
    kaar
    0.50
     شهر
    0.49
     Grayson
    0.49
    Activations Density 0.000%

    No Known Activations