© 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. 13-GEMMASCOPE-2-RES-16K
    7. 536
    Prev
    Next
    INDEX
    Explanations

    kind of

    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_13_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
     c
    1.17
    rightarrow
    1.15
     TODO
    1.14
     :)
    1.14
     derived
    1.14
     q
    1.13
     ->
    1.13
     +
    1.13
     coil
    1.11
     imply
    1.07
    POSITIVE LOGITS
    Meanwhile
    2.56
    Despite
    2.51
    Although
    2.36
    Unlike
    2.32
    此外
    2.31
    Ironically
    2.25
    Dalam
    2.23
    Selain
    2.22
    According
    2.20
    While
    2.19
    Activations Density 1.168%

    No Known Activations