© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7953
    Prev
    Next
    INDEX
    Explanations

    depicting emotions or actions

    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
    ت
    1.27
    t
    1.03
    2
    1.02
    ILE
    0.91
    ست
    0.90
    ले
    0.90
    ाई
    0.89
    1
    0.89
    0
    0.89
     doesn
    0.87
    POSITIVE LOGITS
    小说
    1.00
     grotes
    0.98
     Букови
    0.91
     regiões
    0.91
    stanbul
    0.89
     meticul
    0.89
     vred
    0.88
     putern
    0.87
    rocities
    0.86
     emoc
    0.84
    Activations Density 0.669%

    No Known Activations