© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1506
    Prev
    Next
    INDEX
    Explanations

    web links

    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_17_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
    They
    1.02
     mereka
    0.88
    Do
    0.88
     They
    0.82
    Never
    0.81
    }{}
    0.80
    they
    0.80
    Start
    0.77
    Ils
    0.77
    :]
    0.76
    POSITIVE LOGITS
     πρω
    0.82
    ٰی
    0.74
     atención
    0.70
    ーク
    0.70
     consciência
    0.66
    imiento
    0.66
     applicant
    0.65
     pride
    0.65
     réfl
    0.65
     cogniz
    0.64
    Activations Density 0.031%

    No Known Activations