© 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. 67322
    Prev
    Next
    INDEX
    Explanations

    travel destinations and events

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

    but contrast

    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
    li
    0.54
    lo
    0.53
     धो
    0.44
    apro
    0.43
    w
    0.43
     distinction
    0.43
    ly
    0.42
    ni
    0.42
    lin
    0.42
    la
    0.42
    POSITIVE LOGITS
     durchgeführt
    0.46
     éventuellement
    0.45
     später
    0.45
     extrêmement
    0.43
    ித்து
    0.43
     Chaos
    0.42
     Schrödinger
    0.42
     également
    0.41
     później
    0.41
    圿
    0.41
    Activations Density 0.000%

    No Known Activations