© 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-65K
    7. 48393
    Prev
    Next
    INDEX
    Explanations

    fictional content conditions

    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
    Ꮨ
    0.53
    ﾞ
    0.50
     нейтра
    0.49
    પ
    0.48
     হানি
    0.48
    פ
    0.47
    まず
    0.47
    ್ರಿ
    0.47
    ר
    0.47
    प्या
    0.46
    POSITIVE LOGITS
     Transition
    0.47
     Portfolio
    0.45
     Complexity
    0.45
     Population
    0.45
     individuals
    0.44
     mm
    0.43
     Two
    0.42
     Collective
    0.42
     unlocks
    0.42
     Assemble
    0.42
    Activations Density 0.035%

    No Known Activations