© 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. 2459
    Prev
    Next
    INDEX
    Explanations

    medical advice

    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
    ounds
    0.94
    oni
    0.94
    iri
    0.89
    Req
    0.88
    amm
    0.88
     circunferência
    0.87
    矩
    0.86
     रे
    0.86
    ERE
    0.85
    platte
    0.85
    POSITIVE LOGITS
     subsequ
    1.19
     alliance
    1.18
     conjunction
    1.16
     tailored
    1.13
     alliances
    1.12
     sandwiched
    1.11
     partially
    1.11
     specially
    1.11
     dubbed
    1.11
     Bays
    1.09
    Activations Density 0.013%

    No Known Activations