© 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. 40-GEMMASCOPE-2-RES-262K
    7. 205178
    Prev
    Next
    INDEX
    Explanations

    emojis and cute speech

    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_40_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
    бро
    0.46
    Є
    0.46
     :)
    0.45
     бро
    0.43
    čil
    0.42
    ট্ট
    0.42
    Пере
    0.42
    anged
    0.41
    ^{*}=
    0.41
    alada
    0.40
    POSITIVE LOGITS
    👉
    0.42
     facial
    0.40
     asexual
    0.39
     whites
    0.38
     paralysis
    0.38
     quota
    0.37
    👇
    0.37
    )".
    0.36
     funda
    0.36
     putea
    0.36
    Activations Density 0.004%

    No Known Activations