© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 8360
    Prev
    Next
    INDEX
    Explanations

    Harmonics, messages, Aadhaar, responsibility, inactivated, deals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ین
    1.79
     bisschen
    1.63
    ير
    1.47
     creativo
    1.44
    Thats
    1.42
     miejscu
    1.38
    ج
    1.38
    да
    1.34
    ж
    1.34
    یک
    1.32
    POSITIVE LOGITS
    d
    2.38
    et
    2.16
    b
    2.11
    y
    2.08
    C
    2.08
    R
    1.91
    it
    1.89
    in
    1.86
    at
    1.84
    e
    1.84
    Activations Density 0.000%

    No Known Activations