© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14274
    Prev
    Next
    INDEX
    Explanations

    youtube playlist links

    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_7_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
    า
    2.27
    s
    2.25
    𝑛
    2.18
    র
    2.13
    er
    2.12
    RN
    2.11
    CEM
    2.09
    Eyes
    2.07
    ৮
    2.06
    ilor
    2.03
    POSITIVE LOGITS
     '\\;'
    1.99
     vip
    1.96
    繫
    1.90
     manj
    1.90
    ตาย
    1.88
    ூழ
    1.88
    जनिक
    1.82
    oprol
    1.80
    掛
    1.79
    दार
    1.79
    Activations Density 0.001%

    No Known Activations