© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1958
    Prev
    Next
    INDEX
    Explanations

    offering more details or examples

    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_17_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
    ़
    1.20
     Montgomery
    1.17
    ൊരു
    1.10
     Hallmark
    1.09
     glance
    1.08
     eligible
    1.06
     Ross
    1.06
     dign
    1.06
     confine
    1.05
     NSLog
    1.05
    POSITIVE LOGITS
    مع
    1.24
    s
    1.23
    society
    1.21
    diverse
    1.21
    𝑎
    1.21
    reshape
    1.21
    many
    1.21
    languages
    1.20
    sentences
    1.20
    sweater
    1.19
    Activations Density 0.328%

    No Known Activations