© 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. 73024
    Prev
    Next
    INDEX
    Explanations

    phrases followed by punctuation/detail

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

    programming strings

    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
     iss
    0.48
     inn
    0.47
    ,
    0.45
     as
    0.44
     told
    0.42
     '
    0.42
     coupling
    0.42
     don
    0.41
     child
    0.41
     við
    0.41
    POSITIVE LOGITS
    ขึ้น
    0.51
    㸮
    0.50
    屶
    0.49
    బర్
    0.47
     βαθ
    0.46
    वैज्ञानिक
    0.46
    частли
    0.46
     সেক্ট
    0.46
    綪
    0.46
    রেক
    0.45
    Activations Density 0.001%

    No Known Activations