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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119048
    Prev
    Next
    INDEX
    Explanations

    pointer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    O
    -1.17
    7
    -1.02
     oppose
    -0.93
     wirken
    -0.93
    N
    -0.92
    我不
    -0.92
    4
    -0.92
     nedenle
    -0.91
    ING
    -0.91
    你不
    -0.90
    POSITIVE LOGITS
     pointing
    1.58
    pointing
    1.35
    鮠
    1.15
     bojo
    1.12
    ligator
    1.08
     TÉ
    1.08
     우리
    1.06
     mante
    1.05
    指向
    1.05
     Cité
    1.02
    Activations Density 0.015%

    No Known Activations