© 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. 168960
    Prev
    Next
    INDEX
    Explanations

    foreign phrases and cultural references

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

    declaration commitment response

    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
     Dude
    0.43
     magní
    0.42
     হওয়ায়
    0.41
     దక్షి
    0.41
    movies
    0.41
    侠
    0.41
     स्पोर्ट्स
    0.41
     phenotypes
    0.40
     खूप
    0.40
     tentunya
    0.40
    POSITIVE LOGITS
     falsehood
    0.44
    ◻
    0.42
     lekin
    0.42
    RIK
    0.40
     ㄴ
    0.40
     ouverte
    0.40
     haces
    0.40
    зулта
    0.39
    방법
    0.39
     그러나
    0.39
    Activations Density 0.000%

    No Known Activations