© 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. 138789
    Prev
    Next
    INDEX
    Explanations

    prescriptive modeling, performance goals

    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
    ître
    0.53
    ی
    0.50
     мастера
    0.46
    is
    0.45
    िव
    0.42
    비스
    0.42
     особливо
    0.42
    dört
    0.42
    ilia
    0.41
    iczny
    0.41
    POSITIVE LOGITS
     S
    0.50
     demolished
    0.49
     spille
    0.49
     Rue
    0.48
    )-
    0.46
     Melanie
    0.46
    )+
    0.46
     Saturday
    0.45
     Lebanon
    0.45
     Ore
    0.45
    Activations Density 0.001%

    No Known Activations