© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14270
    Prev
    Next
    INDEX
    Explanations

    conversational phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_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
     (&
    0.88
     reimag
    0.82
     AKA
    0.81
     (“
    0.80
     nestled
    0.80
     Etsy
    0.79
     overarching
    0.79
     staples
    0.78
    /
    0.77
     postseason
    0.76
    POSITIVE LOGITS
    Nowadays
    1.36
    kadang
    1.28
     आजकल
    1.17
    please
    1.16
     pls
    1.15
     Nowadays
    1.15
     nowadays
    1.12
    Pero
    1.10
    Moreover
    1.09
     треба
    1.09
    Activations Density 0.004%

    No Known Activations