© 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. 2457
    Prev
    Next
    INDEX
    Explanations

    ] followed by https

    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
    غط
    2.27
    gevens
    2.26
    optimizer
    2.19
    hell
    2.18
    كور
    2.13
    munderover
    2.12
    ை
    2.10
    ្វ
    2.07
    henol
    2.02
    Viva
    2.02
    POSITIVE LOGITS
    орк
    2.49
    nais
    2.44
    اً
    2.34
    nsk
    2.29
    nymi
    2.27
     singkat
    2.26
    ooo
    2.23
    skie
    2.20
    牘
    2.17
    llll
    2.17
    Activations Density 0.075%

    No Known Activations