© 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. 28137
    Prev
    Next
    INDEX
    Explanations

    recording or GIF

    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
     laminar
    0.51
     uranium
    0.50
     reactors
    0.49
     P
    0.49
     reactor
    0.48
     l
    0.48
     L
    0.47
     frameworks
    0.47
     robot
    0.47
     robots
    0.46
    POSITIVE LOGITS
    ahit
    0.57
    스를
    0.56
    moil
    0.54
    ował
    0.54
    ubu
    0.53
    btnClear
    0.53
    ohu
    0.52
    ৬৫
    0.52
    청
    0.52
     ች
    0.52
    Activations Density 0.000%

    No Known Activations