© 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. 9-GEMMASCOPE-2-RES-262K
    4. 8300
    Prev
    Next
    INDEX
    Explanations

    when questions and conditions

    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_9_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
    žil
    2.77
    ي
    2.63
    ına
    2.62
    ɓ
    2.58
    து
    2.48
     dàng
    2.46
    గా
    2.42
    }$\
    2.42
    祉
    2.40
    owane
    2.40
    POSITIVE LOGITS
     faced
    3.75
    दस्त
    3.41
    र्द
    3.18
     जेव्हा
    3.11
    либо
    3.04
    마다
    3.04
     xưa
    2.97
    𝐫
    2.92
    soever
    2.80
    هما
    2.79
    Activations Density 0.136%

    No Known Activations