© 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. 6910
    Prev
    Next
    INDEX
    Explanations

    group nouns followed by verbs

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

    how things function or act

    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
    +.
    0.20
     আছে
    0.19
     .
    0.19
    2
    0.19
    ৮
    0.18
    ().
    0.18
    .).
    0.18
    **.
    0.18
    也被
    0.18
    -.
    0.18
    POSITIVE LOGITS
     construct
    0.21
     unapolog
    0.20
     gerçekleşt
    0.20
     systematically
    0.18
     constructs
    0.18
     strive
    0.18
     осозна
    0.18
     resolve
    0.18
    不仅
    0.18
     consciously
    0.17
    Activations Density 0.588%

    No Known Activations