© 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-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 163
    Prev
    Next
    INDEX
    Explanations

    path or filename indicators

    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
     Grain
    1.20
     O
    1.19
    жный
    1.14
     düşünü
    1.13
     to
    1.12
    说到
    1.10
     Guy
    1.09
    到了
    1.07
     가까
    1.06
     habló
    1.06
    POSITIVE LOGITS
    <0x06>
    1.51
     PublicKey
    1.46
    തെ
    1.45
    エコ
    1.41
    OMX
    1.41
     invigor
    1.41
    sapp
    1.40
    NoStop
    1.40
     eagerness
    1.40
    ্যান্ড
    1.40
    Activations Density 0.000%

    No Known Activations