© 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. 22-GEMMASCOPE-2-RES-16K
    7. 295
    Prev
    Next
    INDEX
    Explanations

    numbers in lists

    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_22_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
     Holiness
    0.93
    윌
    0.84
     Whis
    0.82
    UTORY
    0.81
    믈
    0.81
    መም
    0.80
     RUT
    0.80
     Tilt
    0.80
    oMatrix
    0.80
     Gost
    0.79
    POSITIVE LOGITS
    cb
    1.76
    c
    1.66
    dc
    1.65
    bcb
    1.64
    bf
    1.64
    bc
    1.64
    fd
    1.63
    bcc
    1.62
    fc
    1.60
    b
    1.60
    Activations Density 1.155%

    No Known Activations