© 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. 244644
    Prev
    Next
    INDEX
    Explanations

    oversized items and sources

    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
    可在
    0.56
    首先
    0.50
     우선
    0.48
    cien
    0.45
    prop
    0.45
     통
    0.45
    Hö
    0.44
    lux
    0.44
    이자
    0.44
    contain
    0.44
    POSITIVE LOGITS
    ності
    0.51
    வ்வளவு
    0.48
    摖
    0.47
    வ்வாற
    0.46
     Rashifal
    0.46
     presentazione
    0.45
     immersing
    0.45
     maneras
    0.43
     искусства
    0.42
     більш
    0.42
    Activations Density 0.001%

    No Known Activations