© 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. 8464
    Prev
    Next
    INDEX
    Explanations

    H followed by common suffixes

    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
    و
    1.35
    u
    1.19
    また
    1.13
    다
    1.07
    وڈ
    1.07
    いません
    1.02
    d
    1.02
    هلاك
    1.00
    cipher
    1.00
     Наи
    0.98
    POSITIVE LOGITS
    acking
    1.17
    ঠাৎ
    1.13
    acked
    1.02
    я
    1.00
     querc
    0.99
    륭
    0.99
    萏
    0.98
    ᱸ
    0.97
    ंगामा
    0.96
     accountable
    0.96
    Activations Density 0.227%

    No Known Activations