© 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. 143629
    Prev
    Next
    INDEX
    Explanations

    academic terms and concepts

    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
    壃
    0.44
    栤
    0.42
    琕
    0.41
    aitement
    0.41
    稩
    0.41
     plufieurs
    0.40
    埶
    0.40
    ейчас
    0.40
    ﻧ
    0.40
    œuf
    0.39
    POSITIVE LOGITS
    :
    0.48
    --
    0.44
     --
    0.42
    ↵
    0.41
    ---
    0.41
    -
    0.41
    5
    0.40
     towns
    0.39
     S
    0.39
    str
    0.38
    Activations Density 0.009%

    No Known Activations