© 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. 139063
    Prev
    Next
    INDEX
    Explanations

    estimate R

    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
     etwas
    0.48
     unjustly
    0.46
     înd
    0.46
    ዣ
    0.45
    Fechar
    0.45
     ইমর
    0.44
     ቦ
    0.44
     ἡ
    0.44
    ientemente
    0.43
    ებენ
    0.43
    POSITIVE LOGITS
    planner
    0.44
    perc
    0.41
    밖
    0.40
    зем
    0.39
     routed
    0.39
    ⊃
    0.39
     supervis
    0.38
    χρι
    0.38
    outside
    0.38
    planning
    0.38
    Activations Density 0.002%

    No Known Activations