© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 125273
    Prev
    Next
    INDEX
    Explanations

    certain word followed by specific word/punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    Ф
    0.50
    Worst
    0.48
    Taiwan
    0.48
    ாராய
    0.47
    Twins
    0.47
    Hiện
    0.46
    Ба
    0.45
    ISTS
    0.45
     বাঙ্গালীর
    0.44
     पर्यटकों
    0.44
    POSITIVE LOGITS
     payroll
    0.44
     to
    0.44
     $'
    0.43
     term
    0.41
     oil
    0.41
     payments
    0.41
     jou
    0.40
     sitcom
    0.40
     cominc
    0.39
     rythme
    0.39
    Activations Density 0.008%

    No Known Activations