© 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. 168601
    Prev
    Next
    INDEX
    Explanations

    safe place or space

    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
    "/"
    0.51
     ihnen
    0.49
     জনগণের
    0.46
    CTS
    0.43
     yıll
    0.42
    继
    0.42
    ពួកគេ
    0.41
     calendriers
    0.41
     यूजी
    0.41
    idz
    0.40
    POSITIVE LOGITS
     haute
    0.45
    யர்
    0.44
    키
    0.40
     veggies
    0.40
    щал
    0.39
    장
    0.39
     savory
    0.39
     Riv
    0.38
    φο
    0.38
     hypnotic
    0.38
    Activations Density 0.003%

    No Known Activations