© 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. 257879
    Prev
    Next
    INDEX
    Explanations

    language that expresses uncertainty or risk, such as framing statements in terms of likelihood, possibility, or perceived threat.

    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
    吕
    0.45
     tri
    0.45
     LU
    0.44
     MAN
    0.44
    ለጠ
    0.43
     Aliexpress
    0.43
     sweetener
    0.42
    enumerate
    0.42
     AN
    0.42
     Li
    0.42
    POSITIVE LOGITS
     আর্মির
    0.46
    dreams
    0.45
     چلے
    0.45
     maio
    0.45
    DejaVu
    0.43
     ۹
    0.41
     границы
    0.41
    ۰۰
    0.41
     Finlandia
    0.40
     территориа
    0.40
    Activations Density 0.005%

    No Known Activations