© 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-262K
    7. 11524
    Prev
    Next
    INDEX
    Explanations

    reverse shell and access

    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_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
    ع
    1.45
     packed
    1.34
    в
    1.29
     thoroughly
    1.29
     swelled
    1.28
     comprehensively
    1.28
     eponymous
    1.25
     headquartered
    1.24
     comprehensive
    1.24
     collectively
    1.21
    POSITIVE LOGITS
    ्स
    1.45
    sung
    1.39
    л
    1.36
    som
    1.29
    ス
    1.26
    ings
    1.21
    inees
    1.20
    ünüz
    1.19
    sy
    1.19
    ึก
    1.18
    Activations Density 0.000%

    No Known Activations