© 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. 1703
    Prev
    Next
    INDEX
    Explanations

    writing actions

    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
    स्तिष्क
    2.60
    я
    2.38
     usize
    2.34
    ר
    2.30
    lollipop
    2.29
     anisotrop
    2.29
    ت
    2.20
    ியா
    2.18
    تهم
    2.16
     ducha
    2.14
    POSITIVE LOGITS
    রা
    2.64
     tắt
    2.42
     koju
    2.32
    యిత
    2.15
     Ajouter
    2.10
    м
    2.08
    多い
    2.06
    াড়
    2.05
    HAV
    2.05
    ifiably
    1.99
    Activations Density 0.279%

    No Known Activations