© 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. 22-GEMMASCOPE-2-RES-262K
    7. 4784
    Prev
    Next
    INDEX
    Explanations

    going to places

    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
    hindi
    0.88
    coming
    0.82
    在此
    0.80
    ämän
    0.80
    amp
    0.78
    ፈ
    0.78
    천
    0.76
    glichen
    0.76
     всему
    0.76
    ในการ
    0.76
    POSITIVE LOGITS
     see
    1.51
     lugares
    1.28
     investigate
    1.26
     admire
    1.20
     inspect
    1.18
     grips
    1.15
     Cuba
    1.12
     곳
    1.11
     celebrate
    1.10
     Greece
    1.09
    Activations Density 0.071%

    No Known Activations