© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10055
    Prev
    Next
    INDEX
    Explanations

    states of being

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

    common aspects, approach C#

    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_40_width_16k_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
     फुटबल
    0.32
    ϩ
    0.30
     vyber
    0.28
    깆
    0.28
    न्देल
    0.27
     ኣ
    0.27
     ఉన్నాయి
    0.27
    맏
    0.27
     whak
    0.27
     그러니까
    0.26
    POSITIVE LOGITS
    .
    0.43
    -
    0.40
    ."
    0.35
    ".
    0.34
    .".
    0.32
    _
    0.32
    “.
    0.31
    .",
    0.30
    .";
    0.30
     a
    0.29
    Activations Density 0.451%

    No Known Activations