© 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-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 546
    Prev
    Next
    INDEX
    Explanations

    details and evaluations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    Liber
    0.72
     લાખ
    0.68
     amine
    0.65
     други
    0.65
    อื่นๆ
    0.64
    Exponential
    0.62
    阴
    0.60
    Antib
    0.60
     большим
    0.60
     اور
    0.59
    POSITIVE LOGITS
     unnecessarily
    0.93
     needlessly
    0.90
     unquestionably
    0.85
     lessened
    0.84
     extravaganza
    0.83
     inasmuch
    0.82
     preclude
    0.81
     pursuant
    0.81
     conspicuously
    0.80
    <unused2122>
    0.79
    Activations Density 6.280%

    No Known Activations