© 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. 16-GEMMASCOPE-2-RES-16K
    7. 407
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    phrases with following words

    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_16_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
    s
    0.62
    wires
    0.53
     nurt
    0.52
    tei
    0.52
     understandings
    0.52
     imperatives
    0.50
    v
    0.50
    मधून
    0.50
    gyi
    0.50
     delimiters
    0.49
    POSITIVE LOGITS
    9
    0.78
    5
    0.74
    0
    0.69
    7
    0.65
    ۶
    0.64
    6
    0.64
    ۵
    0.59
    ۸
    0.58
    8
    0.57
    ۰
    0.55
    Activations Density 0.001%

    No Known Activations