© 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-16K
    7. 2570
    Prev
    Next
    INDEX
    Explanations

    level, type, steps

    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_16k_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
    name
    1.16
    ps
    1.09
    ment
    1.02
    elif
    0.96
    ק
    0.94
    inizin
    0.87
    ination
    0.85
    ac
    0.85
    tr
    0.84
    ía
    0.83
    POSITIVE LOGITS
    IN
    1.33
    U
    1.20
    THING
    1.20
    N
    1.12
    एस
    1.10
     evam
    1.02
     kanan
    1.02
    }])
    1.01
    RICAL
    1.00
     akhir
    0.97
    Activations Density 0.105%

    No Known Activations