© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2994
    Prev
    Next
    INDEX
    Explanations

    signs and context

    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_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
     Neurog
    0.73
     opcao
    0.73
     اختیار
    0.72
    apol
    0.71
    planung
    0.71
     zarządz
    0.71
    构
    0.71
    議題
    0.71
     ضمن
    0.71
     управлять
    0.70
    POSITIVE LOGITS
     clues
    2.40
     signs
    2.22
     indicators
    2.11
    Signs
    2.03
     cues
    2.02
     Signs
    1.99
     признаки
    1.96
     clue
    1.93
     unmistakable
    1.92
     indicator
    1.89
    Activations Density 0.649%

    No Known Activations