© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10362
    Prev
    Next
    INDEX
    Explanations

    sensory descriptors of taste, texture, or subtle qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
    доволь
    1.01
    ると
    0.96
    েই
    0.89
    갑
    0.88
    ໃຫ
    0.88
    ким
    0.88
    gendes
    0.87
    TakePicture
    0.86
    $_
    0.86
    ன்றால்
    0.85
    POSITIVE LOGITS
    indrome
    1.32
    marès
    1.24
    metto
    1.21
    acios
    1.16
    atial
    1.01
     polícia
    0.99
    mares
    0.99
    bearers
    0.97
    ermo
    0.96
    adins
    0.95
    Activations Density 0.015%

    No Known Activations