© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8420
    Prev
    Next
    INDEX
    Explanations

    option d

    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
     disipl
    0.75
    CDM
    0.74
     Dis
    0.73
    BDF
    0.73
     န
    0.73
     Discovery
    0.72
    மாக
    0.71
    Disc
    0.70
    undos
    0.70
     Disc
    0.70
    POSITIVE LOGITS
     d
    3.17
    d
    2.84
     D
    2.42
    D
    2.30
    ｄ
    2.19
    𝐝
    2.03
    𝒅
    1.98
    𝗱
    1.97
    ᴅ
    1.88
    𝚍
    1.76
    Activations Density 0.150%

    No Known Activations