© 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. 8306
    Prev
    Next
    INDEX
    Explanations

    end of code/structure

    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
    у
    1.20
    ंजलि
    1.10
     остальные
    1.03
    いる
    1.02
    ज
    1.02
     allotment
    1.01
    ^\
    1.01
     большая
    1.00
     outbreak
    0.98
    ны
    0.97
    POSITIVE LOGITS
    SerializeField
    1.11
     tatt
    1.06
     natoque
    1.04
    been
    1.03
     been
    1.01
    |}\
    0.97
    lije
    0.96
    టువంటి
    0.93
    @]
    0.91
     χώ
    0.91
    Activations Density 0.004%

    No Known Activations