© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 150043
    Prev
    Next
    INDEX
    Explanations

    followed by specific words

    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_29_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
     чого
    0.76
    になります
    0.74
    әк
    0.73
    倰
    0.72
    くなります
    0.72
    晛
    0.71
    荩
    0.71
     ги
    0.71
    ፁ
    0.70
    érard
    0.70
    POSITIVE LOGITS
     interpolated
    0.93
    Another
    0.92
    shared
    0.88
    Happiness
    0.88
    linked
    0.85
    bonus
    0.85
    Echo
    0.84
    Interpol
    0.84
    aired
    0.83
     Dubna
    0.82
    Activations Density 0.000%

    No Known Activations