© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 44000
    Prev
    Next
    INDEX
    Explanations

    metasploit, Maoist, Droid Cast

    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_16_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
    nome
    1.03
    n
    0.96
    TS
    0.88
    don
    0.86
    u
    0.85
    다
    0.82
    and
    0.80
    drug
    0.78
    a
    0.78
    سل
    0.77
    POSITIVE LOGITS
    போன்ற
    0.63
    一丝
    0.62
    ige
    0.61
    着
    0.61
    一般的
    0.61
     الاست
    0.61
     assimilation
    0.61
    一定的
    0.59
    ğu
    0.59
     ίδια
    0.58
    Activations Density 0.001%

    No Known Activations