© 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. 16-GEMMASCOPE-2-RES-262K
    7. 19392
    Prev
    Next
    INDEX
    Explanations

    too little

    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
     greats
    0.96
    ের
    0.95
    К
    0.94
     contingencies
    0.92
    ה
    0.91
     are
    0.91
    یم
    0.91
     turkeys
    0.91
     warranties
    0.90
     broadcasters
    0.90
    POSITIVE LOGITS
    n
    1.27
    f
    1.26
    am
    1.22
    in
    1.16
    ch
    1.14
    ang
    1.06
    v
    1.05
    p
    1.03
    اين
    0.98
    g
    0.96
    Activations Density 0.005%

    No Known Activations