© 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. 111644
    Prev
    Next
    INDEX
    Explanations

    Handling rules, research, RL, mastering

    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
     franch
    0.45
     KFC
    0.43
    み
    0.43
     microphone
    0.43
    )\}
    0.43
     আহমে
    0.42
     arp
    0.41
    )$
    0.41
    вы
    0.40
    ிகள்
    0.40
    POSITIVE LOGITS
    }=[
    0.48
     economy
    0.46
     അപ
    0.46
    Economy
    0.44
    ྦ
    0.44
    컬
    0.44
    uß
    0.43
    }^{*}=\
    0.43
    获奖
    0.43
     വിദ്യാ
    0.42
    Activations Density 0.002%

    No Known Activations