© 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. 33890
    Prev
    Next
    INDEX
    Explanations

    URLs and financial terms

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

    descriptions of additions or occurrences

    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
    𒁀
    0.43
     उन्ह
    0.43
    BLEND
    0.40
     قض
    0.39
     তিনিই
    0.39
     事業
    0.39
     多い
    0.39
    ALLE
    0.38
    覷
    0.38
    VERE
    0.38
    POSITIVE LOGITS
     adorned
    0.50
     also
    0.46
     another
    0.45
    减轻
    0.45
     aesthetically
    0.44
     ايضا
    0.43
    iamo
    0.43
     freshly
    0.42
     أيضاً
    0.42
     också
    0.42
    Activations Density 0.000%

    No Known Activations