© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1028
    Prev
    Next
    INDEX
    Explanations

    specific nouns or labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    孖
    1.52
    趄
    1.50
     McKin
    1.50
    양이
    1.44
     diarrhoea
    1.42
    孭
    1.41
    šit
    1.36
     reckons
    1.36
     organisers
    1.35
     anagram
    1.34
    POSITIVE LOGITS
    7
    1.78
    6
    1.73
    Diffuse
    1.70
    3
    1.62
    8
    1.62
    4
    1.58
     lieu
    1.55
    quetas
    1.54
    º
    1.49
    ຖານ
    1.47
    Activations Density 1.756%

    No Known Activations