© 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. 814
    Prev
    Next
    INDEX
    Explanations

    immediate guess

    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
     stubbornly
    0.94
     (=
    0.94
     weird
    0.93
     trotz
    0.90
     underlying
    0.89
     strangely
    0.87
     torn
    0.86
     pesky
    0.86
     («
    0.84
     degener
    0.83
    POSITIVE LOGITS
    8
    1.58
    0
    1.52
    6
    1.52
    9
    1.49
    7
    1.43
    5
    1.41
    1
    1.38
    3
    1.31
    4
    1.25
    2
    1.19
    Activations Density 1.213%

    No Known Activations