© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 351
    Prev
    Next
    INDEX
    Explanations

    classic, conservative, modern, socialists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    1
    0.51
    6
    0.46
    2
    0.42
    ה
    0.39
    5
    0.37
    3
    0.37
    కు
    0.36
    ?
    0.34
     said
    0.33
    च्या
    0.33
    POSITIVE LOGITS
     amélior
    0.41
     adicional
    0.37
     Estou
    0.36
    et
    0.35
     Toutefois
    0.35
    ্বন
    0.35
     Cependant
    0.35
    irlo
    0.34
    irai
    0.34
     Eski
    0.34
    Activations Density 0.107%

    No Known Activations