© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79630
    Prev
    Next
    INDEX
    Explanations

    resetting progress for permanent boosts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     ],"
    0.47
    本身
    0.47
    焓
    0.45
    atrol
    0.42
    Ultimately
    0.41
    痊
    0.41
    ሳሪያ
    0.41
    irane
    0.41
    Schedule
    0.40
    变
    0.40
    POSITIVE LOGITS
     evaluated
    0.50
     studied
    0.49
    ᄈ
    0.48
     okresie
    0.46
     unknowingly
    0.46
     improvements
    0.46
     propietarios
    0.46
     surm
    0.46
     students
    0.46
     employs
    0.46
    Activations Density 0.001%

    No Known Activations