© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6546
    Prev
    Next
    INDEX
    Explanations

    indicate which

    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_31_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
     ভাবনা
    0.56
     outlook
    0.54
     ఆలో
    0.52
    ভাব
    0.51
     accumulated
    0.50
     avocado
    0.50
    📈
    0.50
    ндары
    0.49
     avocados
    0.49
    孕
    0.49
    POSITIVE LOGITS
     identification
    2.72
     Identification
    2.58
     identificación
    2.52
     identifica
    2.52
     identific
    2.50
    Identification
    2.48
    identification
    2.45
     identify
    2.41
     identifying
    2.41
    identify
    2.41
    Activations Density 0.755%

    No Known Activations