© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 120606
    Prev
    Next
    INDEX
    Explanations

    concrete, poison, forcing, seeds, mine

    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
    یم
    0.48
     două
    0.47
     fotos
    0.47
     România
    0.47
    한
    0.46
     Noida
    0.46
     kojoj
    0.45
    7
    0.45
     Germans
    0.45
     censored
    0.45
    POSITIVE LOGITS
    reg
    0.45
    tones
    0.45
    toned
    0.45
     поко
    0.45
    towards
    0.44
    starcore
    0.43
     ir
    0.42
    series
    0.42
    severe
    0.42
    з
    0.42
    Activations Density 0.000%

    No Known Activations