© 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. 195146
    Prev
    Next
    INDEX
    Explanations

    fortunately no injuries

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

    no injuries or casualties thankfully

    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
    綽
    0.39
    displaystyle
    0.38
    Echo
    0.38
    তুম
    0.38
    破碎
    0.38
    wq
    0.38
     necro
    0.37
    縈
    0.37
    缟
    0.37
    rå
    0.36
    POSITIVE LOGITS
     thankfully
    0.57
     Thankfully
    0.55
     nobody
    0.51
     ninguém
    0.51
    Thankfully
    0.49
     fortunately
    0.48
     personne
    0.45
     Luckily
    0.45
     luckily
    0.45
     tiredness
    0.44
    Activations Density 0.038%

    No Known Activations