© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 19960
    Prev
    Next
    INDEX
    Explanations

    experience at

    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_65k_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
    _{
    0.59
    ness
    0.51
     polarization
    0.49
     পাইনি
    0.48
     worrisome
    0.48
    weapon
    0.47
     في
    0.47
    weight
    0.47
    {
    0.47
     armor
    0.46
    POSITIVE LOGITS
     będzie
    0.55
     Nicky
    0.53
     होगा
    0.52
    겠죠
    0.52
     должны
    0.52
     carers
    0.52
     olacaktır
    0.49
     देखील
    0.49
     zgodnie
    0.48
     mustn
    0.48
    Activations Density 0.025%

    No Known Activations