© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2479
    Prev
    Next
    INDEX
    Explanations

    clicking an icon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Makanan
    1.13
    イ
    1.12
    Daten
    1.10
     وغيرها
    1.09
    াতাড়ি
    1.08
    સ
    1.07
     regiões
    1.07
     đầy
    1.07
    Setelah
    1.06
    ፨
    1.06
    POSITIVE LOGITS
     peer
    0.86
     aggregating
    0.84
     sometimes
    0.80
     picked
    0.77
     particularly
    0.76
     payoff
    0.76
     legitimately
    0.75
     pick
    0.74
     so
    0.73
     occasionally
    0.73
    Activations Density 0.000%

    No Known Activations