© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 15113
    Prev
    Next
    INDEX
    Explanations

    launching

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

    launching new

    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
    j
    0.71
    _
    0.68
    ect
    0.60
    muscle
    0.58
    of
    0.57
    Muscle
    0.55
    ys
    0.54
     thầy
    0.52
     腰
    0.51
    ock
    0.50
    POSITIVE LOGITS
     launches
    1.41
     launching
    1.30
     launch
    1.28
     launched
    1.28
     lancement
    1.26
    Launching
    1.22
     Launched
    1.19
    Launched
    1.19
    launched
    1.16
     Launch
    1.15
    Activations Density 0.037%

    No Known Activations