© 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. 107565
    Prev
    Next
    INDEX
    Explanations

    specific terms and concepts

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

    legal or financial repercussions

    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
    dır
    0.55
     Кри
    0.49
     expérience
    0.47
     دریافت
    0.47
     często
    0.46
    <0xE2>
    0.46
     sürekli
    0.45
     récentes
    0.45
     En
    0.45
    oczes
    0.45
    POSITIVE LOGITS
     ANOTHER
    0.60
    誰
    0.56
     γιατί
    0.55
     THEIR
    0.53
     liabilities
    0.53
     retaliation
    0.52
    ᱖
    0.51
     ಕಡಿ
    0.51
     WOULD
    0.51
     indictment
    0.50
    Activations Density 0.000%

    No Known Activations