© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4495
    Prev
    Next
    INDEX
    Explanations

    then followed by actions

    np_acts-logits-general · gemini-2.5-flash-lite

    introducing the next step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    {
    0.45
    िंग
    0.44
    ون
    0.42
     जोकि
    0.40
    లో
    0.40
     这是
    0.38
    ému
    0.38
    ing
    0.36
    ﺍ
    0.36
     لیں
    0.36
    POSITIVE LOGITS
    на
    0.60
    ก
    0.44
    k
    0.43
    ne
    0.41
     in
    0.40
    나
    0.39
     on
    0.38
    n
    0.38
    спубли
    0.37
    ки
    0.37
    Activations Density 0.062%

    No Known Activations