© 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. 14411
    Prev
    Next
    INDEX
    Explanations

    with news, good, held

    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
    <bos>
    1.33
    a
    1.26
    o
    1.14
     an
    1.12
    z
    1.06
     U
    1.02
     consumption
    0.99
     harmful
    0.98
     evil
    0.98
     free
    0.98
    POSITIVE LOGITS
    𒋾
    2.32
    <unused1963>
    2.30
    <unused883>
    2.27
    꾻
    2.23
     फ्रैक्शंस
    2.23
    <unused921>
    2.23
    fdPar
    2.22
    InfoPlistPath
    2.22
    뿯
    2.21
    𒊕
    2.21
    Activations Density 2.066%

    No Known Activations