© 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. 17-GEMMASCOPE-2-RES-16K
    4. 2187
    Prev
    Next
    INDEX
    Explanations

    start of model response

    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_17_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
     کردن
    1.31
     tier
    1.22
     απο
    1.20
     ________
    1.19
     ____________
    1.17
    化的
    1.16
    하고자
    1.15
    -<
    1.13
     μικ
    1.13
     το
    1.12
    POSITIVE LOGITS
     blasp
    1.41
    querda
    1.22
     Alguns
    1.21
     treacher
    1.18
    ษ
    1.16
     Farewell
    1.15
    ટું
    1.12
    Alright
    1.11
     Obwohl
    1.11
     Hatter
    1.09
    Activations Density 0.668%

    No Known Activations