© 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. 111161
    Prev
    Next
    INDEX
    Explanations

    assist or provide information

    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
     शकेल
    0.46
    ティスト
    0.46
    牆
    0.44
     storyteller
    0.44
    ώνει
    0.43
     rumor
    0.42
     sogno
    0.41
     defensor
    0.41
    駭
    0.41
     passado
    0.40
    POSITIVE LOGITS
    y
    0.54
    i
    0.47
     obstetric
    0.46
    Poems
    0.45
    Limitations
    0.45
    怀孕
    0.44
    '*
    0.42
     footnotes
    0.42
    conferences
    0.42
    Append
    0.41
    Activations Density 0.017%

    No Known Activations