© 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. 72427
    Prev
    Next
    INDEX
    Explanations

    of, capable of, full of, fitted with

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

    sequence after 'after'

    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
    倠
    0.48
     malattie
    0.44
    adena
    0.44
     infertility
    0.44
     পাবে
    0.43
    岡山
    0.43
     ਗ
    0.42
    ંભ
    0.42
    ランク
    0.41
    ∈
    0.41
    POSITIVE LOGITS
     standout
    0.49
     PlayStation
    0.48
     midway
    0.48
     notable
    0.45
     jugador
    0.45
     secondes
    0.44
     just
    0.44
    暂停
    0.43
    有着
    0.43
     resumption
    0.43
    Activations Density 0.001%

    No Known Activations