© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 887
    Prev
    Next
    INDEX
    Explanations

    method calls after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    1.08
     Guilty
    1.07
    =
    1.06
     clouds
    1.06
     CIS
    1.03
     Bom
    1.02
     Johnny
    1.01
    Za
    1.01
     chunks
    1.01
     Gir
    0.98
    POSITIVE LOGITS
    כל
    1.02
    lower
    1.00
    get
    1.00
    ўна
    0.99
    ᐟ
    0.98
    enangkan
    0.98
    ὗ
    0.96
     έχουν
    0.94
     صعبه
    0.94
    搡
    0.93
    Activations Density 0.284%

    No Known Activations