© 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-65K
    7. 215
    Prev
    Next
    INDEX
    Explanations

    lists and definitions

    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_65k_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
     Sen
    0.77
     Sad
    0.72
     Hom
    0.65
     青
    0.65
     Gran
    0.65
     Essen
    0.65
    早
    0.64
     Red
    0.64
     Blue
    0.63
    真
    0.63
    POSITIVE LOGITS
    The
    0.93
    Symptoms
    0.87
     serta
    0.85
    the
    0.84
    These
    0.82
    and
    0.82
     및
    0.80
     এবং
    0.79
    This
    0.76
     narcissistic
    0.76
    Activations Density 0.001%

    No Known Activations