© 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-65K
    7. 7029
    Prev
    Next
    INDEX
    Explanations

    two [plural noun]

    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_65k_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
    <0x0D>
    0.52
    ázquez
    0.47
    ulares
    0.44
    ່ານ
    0.43
    सिया
    0.43
    ía
    0.42
    adena
    0.42
    leyeceğiz
    0.42
    idades
    0.42
    elson
    0.41
    POSITIVE LOGITS
    ంచెం
    0.47
     "=
    0.47
     Beziehungen
    0.46
     harmonies
    0.44
    㖦
    0.44
    াহতি
    0.44
     carer
    0.43
     dividir
    0.43
    徥
    0.43
    喡
    0.42
    Activations Density 0.002%

    No Known Activations