© 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. 16-GEMMASCOPE-2-RES-262K
    7. 120526
    Prev
    Next
    INDEX
    Explanations

    density, induced, resistant, facing, displace

    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_16_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
    ার
    0.54
    Initialized
    0.52
    čky
    0.50
    ção
    0.50
    ER
    0.49
    能
    0.48
    ة
    0.47
    ac
    0.47
    ą
    0.47
    CV
    0.47
    POSITIVE LOGITS
     postulated
    0.52
     antihy
    0.51
     പറയ
    0.49
    রুখ
    0.49
     artefacts
    0.49
     項
    0.48
     monk
    0.48
     monopole
    0.48
     grossly
    0.47
     downsides
    0.47
    Activations Density 0.000%

    No Known Activations