© 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. 17-GEMMASCOPE-2-RES-16K
    7. 241
    Prev
    Next
    INDEX
    Explanations

    cannot and will not

    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
     และ
    1.36
     және
    1.31
    および
    1.25
    and
    1.24
    和小
    1.24
    及
    1.24
    和
    1.23
     и
    1.23
     及
    1.21
    及其
    1.20
    POSITIVE LOGITS
     consequently
    2.41
     therefore
    2.28
     hopefully
    2.21
     hence
    2.18
     thus
    2.13
     luckily
    2.08
     frankly
    2.07
     thereby
    2.00
     voila
    1.98
     certainly
    1.92
    Activations Density 2.020%

    No Known Activations