Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 636
    Prev
    Next
    INDEX
    Explanations

    share it

    np_acts-logits-general · gemini-2.5-flash-lite

    user input prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     necessario
    0.47
    .
    0.44
    )
    0.44
     criar
    0.43
     necesario
    0.43
     menghadapi
    0.41
    ]
    0.41
     it
    0.40
     It
    0.40
    <0xAB>
    0.40
    POSITIVE LOGITS
    in
    0.50
    m
    0.49
    బాద్
    0.48
    c
    0.46
    टॉप
    0.45
    promotion
    0.42
    w
    0.42
    andidate
    0.42
     इतर
    0.42
    పూర్
    0.41
    Activations Density 5.505%

    No Known Activations