© 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-65K
    7. 601
    Prev
    Next
    INDEX
    Explanations

    words followed by specific suffixes

    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_65k_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
    a
    1.34
    s
    1.23
    an
    1.17
    n
    1.14
    y
    1.14
    ن
    1.10
    l
    1.09
    ي
    1.09
    es
    1.06
    u
    1.06
    POSITIVE LOGITS
     Pusenkoff
    1.59
    𒆜
    1.52
    꼫
    1.52
    ExpNow
    1.51
    jiwarl
    1.50
    𒆸
    1.49
    𒈣
    1.49
    idCliente
    1.48
    𒁯
    1.48
    𒋦
    1.48
    Activations Density 1.031%

    No Known Activations