© 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. 53274
    Prev
    Next
    INDEX
    Explanations

    potential issues

    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
    дан
    0.52
    算出
    0.49
    дь
    0.47
     criteri
    0.43
     dopiero
    0.42
    既存
    0.42
     cultivos
    0.42
    歡
    0.42
    ']->
    0.41
     été
    0.41
    POSITIVE LOGITS
    भाल
    0.46
    මත්
    0.45
     compañ
    0.45
     Absatz
    0.44
     fascia
    0.44
     clockwise
    0.44
     goddesses
    0.44
    arat
    0.43
     ప్రపంచ
    0.43
     stereotypes
    0.43
    Activations Density 0.003%

    No Known Activations