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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 107981
    Prev
    Next
    INDEX
    Explanations

    defining scope and categories

    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
    <0x80>
    0.46
     шпа
    0.45
     सिक्के
    0.43
    ⵃ
    0.42
    腴
    0.41
     मानदंड
    0.41
     belladone
    0.41
     अर्पित
    0.40
    ׄ
    0.40
    გრამ
    0.40
    POSITIVE LOGITS
     velocity
    0.47
     dissipation
    0.45
     ]
    0.44
     Technology
    0.44
     I
    0.44
     pretence
    0.44
     range
    0.43
     coaching
    0.43
     erosion
    0.42
     hill
    0.42
    Activations Density 0.011%

    No Known Activations