© 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. 398
    Prev
    Next
    INDEX
    Explanations

    emotion, Musk, riddles

    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
    Os
    1.32
    Д
    1.25
    Z
    1.20
    Fac
    1.19
    Li
    1.18
    Ju
    1.16
    San
    1.16
    S
    1.15
    Osm
    1.12
     and
    1.12
    POSITIVE LOGITS
     CodeableConcept
    1.63
    োহণ
    1.61
    𐰺
    1.59
    𒇻
    1.57
    记忆
    1.57
    𒀝
    1.56
     söyle
    1.54
    লির
    1.53
     speech
    1.53
    ṑ
    1.53
    Activations Density 0.000%

    No Known Activations