© 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. 22594
    Prev
    Next
    INDEX
    Explanations

    addressing as Mommy/Mistress

    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
     ohmic
    0.46
    起來
    0.45
     ово
    0.44
    localVarPath
    0.42
     ፣
    0.41
    I
    0.41
     remuneration
    0.40
     مثال
    0.40
    рение
    0.40
     .=
    0.40
    POSITIVE LOGITS
    预
    0.46
    Ֆ
    0.46
     Feelings
    0.44
     جدید
    0.44
     அறிவியல்
    0.43
    stä
    0.43
     adlı
    0.43
     Allgemeine
    0.43
    declar
    0.42
    ینه
    0.42
    Activations Density 0.000%

    No Known Activations