Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 31062
    Prev
    Next
    INDEX
    Explanations

    shall followed by verbs

    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
    𝙨
    1.36
    𝙣
    1.34
    ят
    1.30
    ascus
    1.28
     Milestone
    1.27
    yyyy
    1.26
    𝙖
    1.25
    𝙞
    1.25
    써
    1.24
    های
    1.23
    POSITIVE LOGITS
    ある
    1.86
    л
    1.80
    Са
    1.52
    Translatef
    1.49
     vraie
    1.43
    ັບ
    1.41
     sentencia
    1.41
    ल
    1.41
    ૂર્ણ
    1.41
     eigene
    1.39
    Activations Density 0.001%

    No Known Activations