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-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 7271
    Prev
    Next
    INDEX
    Explanations

    emotions and states

    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_16_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
    v
    0.59
    ت
    0.58
    s
    0.55
    <0x93>
    0.53
    uk
    0.49
    í
    0.48
    j
    0.48
    elf
    0.47
    There
    0.46
    What
    0.44
    POSITIVE LOGITS
     Poder
    0.52
     illuminate
    0.50
     permeate
    0.50
    κα
    0.50
    系の
    0.49
     dotato
    0.49
     rattle
    0.49
    તિહાસ
    0.49
     Վ
    0.48
     interdit
    0.48
    Activations Density 0.524%

    No Known Activations