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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2442
    Prev
    Next
    INDEX
    Explanations

    website launch or content

    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_9_width_16k_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
    downcase
    3.16
    ፍተኛ
    2.62
    വ
    2.59
    о
    2.57
    ुरी
    2.54
    ه
    2.45
    л
    2.45
    воен
    2.43
    லி
    2.41
    а
    2.40
    POSITIVE LOGITS
    gameOver
    3.30
    كب
    2.86
    ك
    2.78
     partir
    2.64
     newLine
    2.60
     impulse
    2.55
     aldehydes
    2.51
     symptomatic
    2.51
    ască
    2.49
    ни
    2.47
    Activations Density 0.177%

    No Known Activations