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. 31-GEMMASCOPE-2-RES-262K
    4. 3858
    Prev
    Next
    INDEX
    Explanations

    Linguistically, Краткое

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions and representations of letters/characters—especially isolated or capital letters and diacritic-marked Latin characters—i.e., orthographic letter tokens rather than word-level meaning.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    3
    0.32
    4
    0.31
    5
    0.29
    8
    0.29
    6
    0.28
    9
    0.27
    7
    0.27
    2
    0.27
     (
    0.24
    \
    0.21
    POSITIVE LOGITS
    apayati
    0.19
    ajjati
    0.18
     virulence
    0.18
    趄
    0.18
    agamanam
    0.17
     amni
    0.17
    りが
    0.16
    蛩
    0.16
     монасты
    0.16
     manipular
    0.16
    Activations Density 5.501%

    No Known Activations