© 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. 110918
    Prev
    Next
    INDEX
    Explanations

    logo design, significant progress

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

    imagine, smell, approximation

    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
    ৪
    0.58
    মারের
    0.52
    לק
    0.51
     Nintendo
    0.50
     মণ
    0.50
    ৮
    0.50
     正規品
    0.47
     অঞ্চল
    0.47
    ダイニング
    0.47
     KEYUP
    0.46
    POSITIVE LOGITS
    лли
    0.44
    परेटर
    0.44
    productive
    0.41
     sensitively
    0.41
    前
    0.41
    pra
    0.40
     terrestre
    0.40
    fore
    0.40
     тихо
    0.39
     fundament
    0.39
    Activations Density 0.001%

    No Known Activations