© 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. 13-GEMMASCOPE-2-RES-16K
    7. 4284
    Prev
    Next
    INDEX
    Explanations

    still

    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
    ה
    2.25
    𝒐
    2.16
    ている
    2.12
    larda
    2.09
    збеки
    2.09
    ে
    2.09
    𝒆
    2.08
    蜒
    2.06
    ட்டிக்க
    2.04
    ాం
    2.04
    POSITIVE LOGITS
    erman
    2.13
    erm
    1.99
    üe
    1.92
    epan
    1.91
    ered
    1.90
     reeling
    1.89
    ingt
    1.89
    aling
    1.88
    ᴇ
    1.87
    ัล
    1.84
    Activations Density 0.212%

    No Known Activations