© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 84127
    Prev
    Next
    INDEX
    Explanations

    shooting at targets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vaulted
    0.41
     itali
    0.38
     Italian
    0.38
    ஷா
    0.37
     Assembly
    0.37
     choke
    0.37
     possession
    0.36
    숄
    0.36
    stored
    0.35
     italian
    0.35
    POSITIVE LOGITS
     targets
    0.70
    靶
    0.67
     Targets
    0.65
     टारगेट
    0.63
     target
    0.62
    Targets
    0.59
     Target
    0.59
    targets
    0.58
     TARGET
    0.57
     cible
    0.57
    Activations Density 0.013%

    No Known Activations